Skip to main content
Glama
Sign In

FAHCE Integrity Repair

by com.kinganlogic
OverviewDiscussionsAdmin

Server Details

Free FAHCE contract discovery. Paid evidence determinations use wallet-only x402 REST endpoints.

Ownership verified
Status
Healthy
Uptime
100.0% over 18 days
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

B3.3/5.0

Scored across 4 tools

Disambiguation4/5

Each tool maps to a distinct pipeline stage (diagnose, plan, verify) and descriptions give concrete examples. The repair_bundle tool overlaps all three by combining diagnosis, correction proposal, and verification, so an agent could plausibly pick it instead of the single-stage tools.

Naming Consistency4/5

All names use snake_case with a uniform fahce_ prefix, which is predictable. However, three follow a verb_first pattern (diagnose_integrity, plan_bounded_repair, verify_repaired_output) while integrity_repair_bundle is noun-first, a minor structural deviation.

Tool Count4/5

Four tools form a tight, well-scoped set around a single workflow, with each stage earning its place. It is slightly lean, and the bundle tool is arguably redundant with the three single-stage tools.

Completeness3/5

Diagnosis, planning, verification, and a combined bundle are covered, but there is no tool to actually apply or execute a repair, and no tool to retrieve or list previously issued receipts. For a server named 'Integrity Repair', the absence of an execution step leaves the workflow terminating at a proposal.

Available Tools

4 tools
fahce_diagnose_integrityB
Idempotent
Inspect

Discover evidence-based claim diagnosis via x402 POST /api/v1/diagnose. Returns findings and a receipt. Example: claimed success versus a failure log.

NameRequiredDescriptionDefault
requestYesREST body only; maximum 524288 UTF-8 bytes for the complete serialized body. Field limits also apply.
idempotency_keyNoREST retry key; reuse only for identical operation, input, and authorization.

Output Schema

NameRequiredDescription
repairYes
schemaYes
billingYes
bindingNo
receiptYes
authorityNo
diagnosisYes
operationYes
input_hashYes
request_idYesDetermination ID; equals receipt.case_id/run_id and identifies the saved receipt. Error request_id is a separate trace.
attestationNo
verificationYes
execution_stateNo
next_safe_actionYes
evidence_provenanceNo

TDQS

B3.4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds real value beyond annotations by disclosing that this is an x402 (paid) POST endpoint and that the response includes a receipt, neither of which appears in the annotations. However, it does not explain the payment/authorization requirement in practical terms, what the receipt is, or why readOnlyHint is false for what looks like a diagnostic read.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences with the core action and endpoint front-loaded, then the return shape, then a concrete example. No filler, though 'Discover' is slightly vague framing for what is a direct call.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and full schema coverage, the description needn't explain return values, and it doesn't have to. But for a tool sitting in a family of four related integrity tools with a paid x402 call, the missing routing guidance and cost/authorization expectation leave a real gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, including detailed notes on evidence, candidate_output, expected_output and idempotency_key, so the schema does the heavy lifting. The description adds no parameter-level guidance beyond the example payload, which the schema already carries as an example.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb+resource ('claim diagnosis') and concretizes it with the endpoint (x402 POST /api/v1/diagnose) and an example ('claimed success versus a failure log'). It does not explicitly differentiate itself from siblings like fahce_verify_repaired_output or fahce_integrity_repair_bundle, so an agent must infer the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied by the example scenario (a claimed success checked against a failure log); there is no statement of when to choose this over fahce_verify_repaired_output or fahce_plan_bounded_repair, and no prerequisites or exclusions are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

fahce_integrity_repair_bundleA
Idempotent
Inspect

Discover combined diagnosis, proposed correction, and verification via x402 POST /api/v1/repair-bundle. Example: resolve a disputed completion claim. No repair executes.

NameRequiredDescriptionDefault
requestYesREST body only; maximum 524288 UTF-8 bytes for the complete serialized body. Field limits also apply.
idempotency_keyNoREST retry key; reuse only for identical operation, input, and authorization.

Output Schema

NameRequiredDescription
repairYes
schemaYes
billingYes
bindingNo
receiptYes
authorityNo
diagnosisYes
operationYes
input_hashYes
request_idYesDetermination ID; equals receipt.case_id/run_id and identifies the saved receipt. Error request_id is a separate trace.
attestationNo
verificationYes
execution_stateNo
next_safe_actionYes
evidence_provenanceNo

TDQS

A3.6/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The key behavioral disclosure is 'No repair executes,' which usefully tempers what the name 'repair_bundle' might otherwise imply. The annotations already cover safety traits like destructiveHint=false and idempotentHint=true, but the description does not explain the x402 payment/authorization implications of the POST endpoint, which is important for a tool with readOnlyHint=false.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three short sentences with the operation, example, and critical non-execution caveat front-loaded. Every sentence contributes useful information without repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex nested schema with an output schema available, the description supplies the essential operational summary, an example, and the no-repair caveat. It could be more complete by clarifying combined-tool versus sibling-tool routing, but the structured fields already carry most detailed semantics.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both parameters and nested request fields are already well documented in the input schema. The description adds no parameter-specific syntax or format guidance beyond the schema, which is acceptable given full coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific combined operation: diagnosis, proposed correction, and verification via a repair-bundle endpoint. It distinguishes itself implicitly from the three single-purpose siblings by being a bundle, though it does not explicitly route agents to or away from those siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The example 'resolve a disputed completion claim' implies a usage context, and 'No repair executes' clarifies that this is discovery rather than mutation. However, there is no explicit guidance on when to use this combined tool versus fahce_diagnose_integrity, fahce_plan_bounded_repair, or fahce_verify_repaired_output.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

fahce_plan_bounded_repairC
Idempotent
Inspect

Discover correction planning via x402 POST /api/v1/repair. Returns an evidence-preserving proposal and receipt. Example: correct a contradicted success claim.

NameRequiredDescriptionDefault
requestYesREST body only; maximum 524288 UTF-8 bytes for the complete serialized body. Field limits also apply.
idempotency_keyNoREST retry key; reuse only for identical operation, input, and authorization.

Output Schema

NameRequiredDescription
repairYes
schemaYes
billingYes
bindingNo
receiptYes
authorityNo
diagnosisYes
operationYes
input_hashYes
request_idYesDetermination ID; equals receipt.case_id/run_id and identifies the saved receipt. Error request_id is a separate trace.
attestationNo
verificationYes
execution_stateNo
next_safe_actionYes
evidence_provenanceNo

TDQS

C2.9/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare idempotentHint=true, destructiveHint=false, and readOnlyHint=false. The description adds real value by signaling an x402 POST (i.e., a paid, non-read-only endpoint) and stating the return shape ('evidence-preserving proposal and receipt'). However, it never states that a payment/authorization step is required or what it costs, which is the key behavioral fact for an x402 endpoint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences with no padding, and the purpose is front-loaded before the example. The endpoint path is arguably noise for an agent, but overall it is tight and efficiently structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values needn't be spelled out, and the nested request schema is thoroughly documented. What is missing for this complex, paid, multi-stage workflow is the placement relative to siblings and the payment/authorization prerequisite.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the nested schema documents schema constant, evidence items, candidate_output, and idempotency_key in detail. The description adds no parameter-level meaning beyond the schema, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a resource (correction planning) and an example use case (correcting a contradicted success claim), but the verb 'Discover' is vague and the HTTP endpoint reference ('x402 POST /api/v1/repair') does little to clarify intent. It never distinguishes this planning step from siblings like fahce_diagnose_integrity, fahce_integrity_repair_bundle, or fahce_verify_repaired_output.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is a single example of when the tool might apply, but no explicit when-to-use or when-not-to-use guidance, and no routing against the three sibling tools that cover adjacent stages (diagnose, bundle, verify). The agent must infer the workflow position of this 'plan' step.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

fahce_verify_repaired_outputB
Idempotent
Inspect

Discover submitted-answer verification via x402 POST /api/v1/verify. Returns evidence-bounded findings and a receipt. Example: check a revised deployment status.

NameRequiredDescriptionDefault
requestYesREST body only; maximum 524288 UTF-8 bytes for the complete serialized body. Field limits also apply.
idempotency_keyNoREST retry key; reuse only for identical operation, input, and authorization.

Output Schema

NameRequiredDescription
repairYes
schemaYes
billingYes
bindingNo
receiptYes
authorityNo
diagnosisYes
operationYes
input_hashYes
request_idYesDetermination ID; equals receipt.case_id/run_id and identifies the saved receipt. Error request_id is a separate trace.
attestationNo
verificationYes
execution_stateNo
next_safe_actionYes
evidence_provenanceNo

TDQS

B3.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare that this is a non-read-only, idempotent, non-destructive, closed-world operation. The description adds the endpoint and that the result includes evidence-bounded findings and a receipt, but it does not explain authorization, payment/x402 implications, rate limits, or what happens on retry beyond what annotations cover.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and front-loads the operation and endpoint. The return-behavior sentence and example are relevant, though the opening word 'Discover' is slightly awkward and the example adds limited detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With a rich nested input schema, full parameter description coverage, annotations, and an output schema, the description is minimally adequate. However, for a verification tool with nearby diagnostic and repair siblings, it omits guidance about when this tool is the correct choice, leaving a contextual gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema itself fully documents the request structure, evidence fields, candidate_output, expected_output, and idempotency_key. The description does not add parameter-level meaning beyond the schema's own descriptions, making the baseline 3 appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific operation and resource: submitted-answer verification via POST /api/v1/verify, returning evidence-bounded findings and a receipt. The example clarifies a concrete use case. It does not explicitly differentiate this tool from sibling repair/diagnostic tools, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives an example use case but does not state when to use this tool versus the sibling tools fahce_diagnose_integrity, fahce_plan_bounded_repair, or fahce_integrity_repair_bundle. There are no explicit when-not or alternative-selection guidelines.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 4 tool updates
    • Changedfahce_diagnose_integrity4 fields changed
      • changedInput schema / examples
        Previous value: -[
-  {
-    "request": {
-      "candidate_output": "Deployment completed successfully.",
-      "evidence": [
-        {
-          "id": "deployment_log",
-          "kind": "log",
-          "source_label": "independent deployment log",
-          "text": "Deployment failed."
-        }
-      ],
-      "schema": "FAHCE_MACHINE_REQUEST_V1"
-    }
-  }
-]New value: +[
+  {
+    "request": {
+      "candidate_output": "Deployment completed successfully.",
+      "evidence": [
+        {
+          "id": "deployment_log",
+          "kind": "log",
+          "source_label": "caller-supplied deployment log",
+          "text": "Deployment failed."
+        }
+      ],
+      "schema": "FAHCE_MACHINE_REQUEST_V1"
+    }
+  }
+]
      • changedInput schema / properties / idempotency_key / description
        Previous value: -"Optional REST Idempotency-Key. Reuse only with unchanged operation, input, and authorization; recover saved results after uncertain delivery."New value: +"REST retry key; reuse only for identical operation, input, and authorization."
      • changedInput schema / properties / request / description
        Previous value: -"Send this request object alone to the paid REST endpoint. Entire JSON must fit 524288 UTF-8 bytes, including MCP wrapper, labels and escaping; per-field ceilings cannot all be used together. Character limits use UTF-16 code units."New value: +"REST body only; maximum 524288 UTF-8 bytes for the complete serialized body. Field limits also apply."
      • changedOutput schema / properties / request_id / description
        Previous value: -"Determination UUID, identical to receipt.case_id and receipt.run_id. Use this UUID as receipt_id in GET /api/v1/receipts/{receipt_id}. Error-envelope request_id is a separate HTTP trace; use its receipt_id when present."New value: +"Determination ID; equals receipt.case_id/run_id and identifies the saved receipt. Error request_id is a separate trace."
    • Changedfahce_integrity_repair_bundle4 fields changed
      • changedInput schema / examples
        Previous value: -[
-  {
-    "request": {
-      "candidate_output": "Deployment completed successfully.",
-      "evidence": [
-        {
-          "id": "deployment_log",
-          "kind": "log",
-          "source_label": "independent deployment log",
-          "text": "Deployment failed."
-        }
-      ],
-      "schema": "FAHCE_MACHINE_REQUEST_V1"
-    }
-  }
-]New value: +[
+  {
+    "request": {
+      "candidate_output": "Deployment completed successfully.",
+      "evidence": [
+        {
+          "id": "deployment_log",
+          "kind": "log",
+          "source_label": "caller-supplied deployment log",
+          "text": "Deployment failed."
+        }
+      ],
+      "schema": "FAHCE_MACHINE_REQUEST_V1"
+    }
+  }
+]
      • changedInput schema / properties / idempotency_key / description
        Previous value: -"Optional REST Idempotency-Key. Reuse only with unchanged operation, input, and authorization; recover saved results after uncertain delivery."New value: +"REST retry key; reuse only for identical operation, input, and authorization."
      • changedInput schema / properties / request / description
        Previous value: -"Send this request object alone to the paid REST endpoint. Entire JSON must fit 524288 UTF-8 bytes, including MCP wrapper, labels and escaping; per-field ceilings cannot all be used together. Character limits use UTF-16 code units."New value: +"REST body only; maximum 524288 UTF-8 bytes for the complete serialized body. Field limits also apply."
      • changedOutput schema / properties / request_id / description
        Previous value: -"Determination UUID, identical to receipt.case_id and receipt.run_id. Use this UUID as receipt_id in GET /api/v1/receipts/{receipt_id}. Error-envelope request_id is a separate HTTP trace; use its receipt_id when present."New value: +"Determination ID; equals receipt.case_id/run_id and identifies the saved receipt. Error request_id is a separate trace."
    • Changedfahce_plan_bounded_repair4 fields changed
      • changedInput schema / examples
        Previous value: -[
-  {
-    "request": {
-      "candidate_output": "Deployment completed successfully.",
-      "evidence": [
-        {
-          "id": "deployment_log",
-          "kind": "log",
-          "source_label": "independent deployment log",
-          "text": "Deployment failed."
-        }
-      ],
-      "schema": "FAHCE_MACHINE_REQUEST_V1"
-    }
-  }
-]New value: +[
+  {
+    "request": {
+      "candidate_output": "Deployment completed successfully.",
+      "evidence": [
+        {
+          "id": "deployment_log",
+          "kind": "log",
+          "source_label": "caller-supplied deployment log",
+          "text": "Deployment failed."
+        }
+      ],
+      "schema": "FAHCE_MACHINE_REQUEST_V1"
+    }
+  }
+]
      • changedInput schema / properties / idempotency_key / description
        Previous value: -"Optional REST Idempotency-Key. Reuse only with unchanged operation, input, and authorization; recover saved results after uncertain delivery."New value: +"REST retry key; reuse only for identical operation, input, and authorization."
      • changedInput schema / properties / request / description
        Previous value: -"Send this request object alone to the paid REST endpoint. Entire JSON must fit 524288 UTF-8 bytes, including MCP wrapper, labels and escaping; per-field ceilings cannot all be used together. Character limits use UTF-16 code units."New value: +"REST body only; maximum 524288 UTF-8 bytes for the complete serialized body. Field limits also apply."
      • changedOutput schema / properties / request_id / description
        Previous value: -"Determination UUID, identical to receipt.case_id and receipt.run_id. Use this UUID as receipt_id in GET /api/v1/receipts/{receipt_id}. Error-envelope request_id is a separate HTTP trace; use its receipt_id when present."New value: +"Determination ID; equals receipt.case_id/run_id and identifies the saved receipt. Error request_id is a separate trace."
    • Changedfahce_verify_repaired_output4 fields changed
      • changedInput schema / examples
        Previous value: -[
-  {
-    "request": {
-      "candidate_output": "Deployment failed.",
-      "evidence": [
-        {
-          "id": "deployment_log",
-          "kind": "log",
-          "source_label": "independent deployment log",
-          "text": "Deployment failed."
-        }
-      ],
-      "schema": "FAHCE_MACHINE_REQUEST_V1"
-    }
-  }
-]New value: +[
+  {
+    "request": {
+      "candidate_output": "Deployment failed.",
+      "evidence": [
+        {
+          "id": "deployment_log",
+          "kind": "log",
+          "source_label": "caller-supplied deployment log",
+          "text": "Deployment failed."
+        }
+      ],
+      "schema": "FAHCE_MACHINE_REQUEST_V1"
+    }
+  }
+]
      • changedInput schema / properties / idempotency_key / description
        Previous value: -"Optional REST Idempotency-Key. Reuse only with unchanged operation, input, and authorization; recover saved results after uncertain delivery."New value: +"REST retry key; reuse only for identical operation, input, and authorization."
      • changedInput schema / properties / request / description
        Previous value: -"Send this request object alone to the paid REST endpoint. Entire JSON must fit 524288 UTF-8 bytes, including MCP wrapper, labels and escaping; per-field ceilings cannot all be used together. Character limits use UTF-16 code units."New value: +"REST body only; maximum 524288 UTF-8 bytes for the complete serialized body. Field limits also apply."
      • changedOutput schema / properties / request_id / description
        Previous value: -"Determination UUID, identical to receipt.case_id and receipt.run_id. Use this UUID as receipt_id in GET /api/v1/receipts/{receipt_id}. Error-envelope request_id is a separate HTTP trace; use its receipt_id when present."New value: +"Determination ID; equals receipt.case_id/run_id and identifies the saved receipt. Error request_id is a separate trace."
  2. 4 tool updates
    • Changedfahce_diagnose_integrity2 fields changed
      • addedInput schema / examples
        Added value: +[
+  {
+    "request": {
+      "candidate_output": "Deployment completed successfully.",
+      "evidence": [
+        {
+          "id": "deployment_log",
+          "kind": "log",
+          "source_label": "independent deployment log",
+          "text": "Deployment failed."
+        }
+      ],
+      "schema": "FAHCE_MACHINE_REQUEST_V1"
+    }
+  }
+]
      • changedInput schema / properties / idempotency_key / description
        Previous value: -"Optional REST Idempotency-Key; bind unchanged operation, input and authorization. Reuse conflicts on changes; recover saved results instead of paying again."New value: +"Optional REST Idempotency-Key. Reuse only with unchanged operation, input, and authorization; recover saved results after uncertain delivery."
    • Changedfahce_integrity_repair_bundle2 fields changed
      • addedInput schema / examples
        Added value: +[
+  {
+    "request": {
+      "candidate_output": "Deployment completed successfully.",
+      "evidence": [
+        {
+          "id": "deployment_log",
+          "kind": "log",
+          "source_label": "independent deployment log",
+          "text": "Deployment failed."
+        }
+      ],
+      "schema": "FAHCE_MACHINE_REQUEST_V1"
+    }
+  }
+]
      • changedInput schema / properties / idempotency_key / description
        Previous value: -"Optional REST Idempotency-Key; bind unchanged operation, input and authorization. Reuse conflicts on changes; recover saved results instead of paying again."New value: +"Optional REST Idempotency-Key. Reuse only with unchanged operation, input, and authorization; recover saved results after uncertain delivery."
    • Changedfahce_plan_bounded_repair2 fields changed
      • addedInput schema / examples
        Added value: +[
+  {
+    "request": {
+      "candidate_output": "Deployment completed successfully.",
+      "evidence": [
+        {
+          "id": "deployment_log",
+          "kind": "log",
+          "source_label": "independent deployment log",
+          "text": "Deployment failed."
+        }
+      ],
+      "schema": "FAHCE_MACHINE_REQUEST_V1"
+    }
+  }
+]
      • changedInput schema / properties / idempotency_key / description
        Previous value: -"Optional REST Idempotency-Key; bind unchanged operation, input and authorization. Reuse conflicts on changes; recover saved results instead of paying again."New value: +"Optional REST Idempotency-Key. Reuse only with unchanged operation, input, and authorization; recover saved results after uncertain delivery."
    • Changedfahce_verify_repaired_output2 fields changed
      • addedInput schema / examples
        Added value: +[
+  {
+    "request": {
+      "candidate_output": "Deployment failed.",
+      "evidence": [
+        {
+          "id": "deployment_log",
+          "kind": "log",
+          "source_label": "independent deployment log",
+          "text": "Deployment failed."
+        }
+      ],
+      "schema": "FAHCE_MACHINE_REQUEST_V1"
+    }
+  }
+]
      • changedInput schema / properties / idempotency_key / description
        Previous value: -"Optional REST Idempotency-Key; bind unchanged operation, input and authorization. Reuse conflicts on changes; recover saved results instead of paying again."New value: +"Optional REST Idempotency-Key. Reuse only with unchanged operation, input, and authorization; recover saved results after uncertain delivery."
  3. 4 tool updates
    • Changedfahce_diagnose_integrity12 fields changed
      • removedInput schema / examples
        Removed value: -[
-  {
-    "request": {
-      "candidate_output": "Deployment completed successfully.",
-      "evidence": [
-        {
-          "id": "deployment_log",
-          "kind": "log",
-          "source_label": "independent deployment log",
-          "text": "Deployment failed."
-        }
-      ],
-      "schema": "FAHCE_MACHINE_REQUEST_V1"
-    }
-  }
-]
      • changedInput schema / properties / idempotency_key / description
        Previous value: -"Optional REST Idempotency-Key. Reuse only with unchanged operation, input, and authorization; recover saved results after uncertain delivery."New value: +"Optional REST Idempotency-Key; bind unchanged operation, input and authorization. Reuse conflicts on changes; recover saved results instead of paying again."
      • changedInput schema / properties / request / description
        Previous value: -"Answer and supporting records for REST review. Whole request: 524288 UTF-8 bytes including the MCP wrapper; character limits use UTF-16 code units."New value: +"Send this request object alone to the paid REST endpoint. Entire JSON must fit 524288 UTF-8 bytes, including MCP wrapper, labels and escaping; per-field ceilings cannot all be used together. Character limits use UTF-16 code units."
      • changedInput schema / properties / request / properties / candidate_output / description
        Previous value: -"Answer to diagnose, correct, or recheck; for Verify, supply the revised answer."New value: +"The exact candidate output to diagnose or verify. Never use payment evidence as semantic evidence."
      • changedInput schema / properties / request / properties / evidence / description
        Previous value: -"Up to 12 caller-supplied records. No sources are fetched or authenticated; an empty list provides no corroboration."New value: +"Caller-supplied records; sources are not authenticated or fetched. An empty array supplies no corroboration."
      • changedInput schema / properties / request / properties / evidence / items / properties / claim_bearing / description
        Previous value: -"True treats this record as claims to check. False or omission does not override candidate-source labels."New value: +"True marks candidate claims, not corroboration. False or omission does not override candidate-source labels."
      • changedInput schema / properties / request / properties / evidence / items / properties / id / description
        Previous value: -"Unique evidence reference within this request, such as deployment_log."New value: +"Unique evidence identifier within this request."
      • changedInput schema / properties / request / properties / evidence / items / properties / kind / description
        Previous value: -"How this record is represented: log, pasted text, document, or description; this does not set its trust level."New value: +"Record format category, not a trust level."
      • changedInput schema / properties / request / properties / evidence / items / properties / source_label / description
        Previous value: -"Record attribution, such as deployment log; candidate/output labels identify claims rather than independent corroboration."New value: +"Source attribution; candidate/output labels mark untrusted claims, not independent proof."
      • changedInput schema / properties / request / properties / evidence / items / properties / text / description
        Previous value: -"Record content used to assess the answer; payment authorization is not semantic evidence."New value: +"Record content to review; never payment authorization as semantic proof."
      • changedInput schema / properties / request / properties / expected_output / description
        Previous value: -"Optional format directives or correction target; factual text here is not corroborating evidence."New value: +"Optional format/constraint and repair-target context for all operations, including Diagnose. Recognized directives (e.g. Return JSON) can affect diagnosis. Factual text is not compared for string equality or trusted as evidence; supply independent records."
      • changedInput schema / properties / request / properties / schema / description
        Previous value: -"Exact FAHCE request contract identifier."New value: +"Request contract identifier; use this exact value."
    • Changedfahce_integrity_repair_bundle12 fields changed
      • removedInput schema / examples
        Removed value: -[
-  {
-    "request": {
-      "candidate_output": "Deployment completed successfully.",
-      "evidence": [
-        {
-          "id": "deployment_log",
-          "kind": "log",
-          "source_label": "independent deployment log",
-          "text": "Deployment failed."
-        }
-      ],
-      "schema": "FAHCE_MACHINE_REQUEST_V1"
-    }
-  }
-]
      • changedInput schema / properties / idempotency_key / description
        Previous value: -"Optional REST Idempotency-Key. Reuse only with unchanged operation, input, and authorization; recover saved results after uncertain delivery."New value: +"Optional REST Idempotency-Key; bind unchanged operation, input and authorization. Reuse conflicts on changes; recover saved results instead of paying again."
      • changedInput schema / properties / request / description
        Previous value: -"Answer and supporting records for REST review. Whole request: 524288 UTF-8 bytes including the MCP wrapper; character limits use UTF-16 code units."New value: +"Send this request object alone to the paid REST endpoint. Entire JSON must fit 524288 UTF-8 bytes, including MCP wrapper, labels and escaping; per-field ceilings cannot all be used together. Character limits use UTF-16 code units."
      • changedInput schema / properties / request / properties / candidate_output / description
        Previous value: -"Answer to diagnose, correct, or recheck; for Verify, supply the revised answer."New value: +"The exact candidate output to diagnose or verify. Never use payment evidence as semantic evidence."
      • changedInput schema / properties / request / properties / evidence / description
        Previous value: -"Up to 12 caller-supplied records. No sources are fetched or authenticated; an empty list provides no corroboration."New value: +"Caller-supplied records; sources are not authenticated or fetched. An empty array supplies no corroboration."
      • changedInput schema / properties / request / properties / evidence / items / properties / claim_bearing / description
        Previous value: -"True treats this record as claims to check. False or omission does not override candidate-source labels."New value: +"True marks candidate claims, not corroboration. False or omission does not override candidate-source labels."
      • changedInput schema / properties / request / properties / evidence / items / properties / id / description
        Previous value: -"Unique evidence reference within this request, such as deployment_log."New value: +"Unique evidence identifier within this request."
      • changedInput schema / properties / request / properties / evidence / items / properties / kind / description
        Previous value: -"How this record is represented: log, pasted text, document, or description; this does not set its trust level."New value: +"Record format category, not a trust level."
      • changedInput schema / properties / request / properties / evidence / items / properties / source_label / description
        Previous value: -"Record attribution, such as deployment log; candidate/output labels identify claims rather than independent corroboration."New value: +"Source attribution; candidate/output labels mark untrusted claims, not independent proof."
      • changedInput schema / properties / request / properties / evidence / items / properties / text / description
        Previous value: -"Record content used to assess the answer; payment authorization is not semantic evidence."New value: +"Record content to review; never payment authorization as semantic proof."
      • changedInput schema / properties / request / properties / expected_output / description
        Previous value: -"Optional format directives or correction target; factual text here is not corroborating evidence."New value: +"Optional format/constraint and repair-target context for all operations, including Diagnose. Recognized directives (e.g. Return JSON) can affect diagnosis. Factual text is not compared for string equality or trusted as evidence; supply independent records."
      • changedInput schema / properties / request / properties / schema / description
        Previous value: -"Exact FAHCE request contract identifier."New value: +"Request contract identifier; use this exact value."
    • Changedfahce_plan_bounded_repair12 fields changed
      • removedInput schema / examples
        Removed value: -[
-  {
-    "request": {
-      "candidate_output": "Deployment completed successfully.",
-      "evidence": [
-        {
-          "id": "deployment_log",
-          "kind": "log",
-          "source_label": "independent deployment log",
-          "text": "Deployment failed."
-        }
-      ],
-      "schema": "FAHCE_MACHINE_REQUEST_V1"
-    }
-  }
-]
      • changedInput schema / properties / idempotency_key / description
        Previous value: -"Optional REST Idempotency-Key. Reuse only with unchanged operation, input, and authorization; recover saved results after uncertain delivery."New value: +"Optional REST Idempotency-Key; bind unchanged operation, input and authorization. Reuse conflicts on changes; recover saved results instead of paying again."
      • changedInput schema / properties / request / description
        Previous value: -"Answer and supporting records for REST review. Whole request: 524288 UTF-8 bytes including the MCP wrapper; character limits use UTF-16 code units."New value: +"Send this request object alone to the paid REST endpoint. Entire JSON must fit 524288 UTF-8 bytes, including MCP wrapper, labels and escaping; per-field ceilings cannot all be used together. Character limits use UTF-16 code units."
      • changedInput schema / properties / request / properties / candidate_output / description
        Previous value: -"Answer to diagnose, correct, or recheck; for Verify, supply the revised answer."New value: +"The exact candidate output to diagnose or verify. Never use payment evidence as semantic evidence."
      • changedInput schema / properties / request / properties / evidence / description
        Previous value: -"Up to 12 caller-supplied records. No sources are fetched or authenticated; an empty list provides no corroboration."New value: +"Caller-supplied records; sources are not authenticated or fetched. An empty array supplies no corroboration."
      • changedInput schema / properties / request / properties / evidence / items / properties / claim_bearing / description
        Previous value: -"True treats this record as claims to check. False or omission does not override candidate-source labels."New value: +"True marks candidate claims, not corroboration. False or omission does not override candidate-source labels."
      • changedInput schema / properties / request / properties / evidence / items / properties / id / description
        Previous value: -"Unique evidence reference within this request, such as deployment_log."New value: +"Unique evidence identifier within this request."
      • changedInput schema / properties / request / properties / evidence / items / properties / kind / description
        Previous value: -"How this record is represented: log, pasted text, document, or description; this does not set its trust level."New value: +"Record format category, not a trust level."
      • changedInput schema / properties / request / properties / evidence / items / properties / source_label / description
        Previous value: -"Record attribution, such as deployment log; candidate/output labels identify claims rather than independent corroboration."New value: +"Source attribution; candidate/output labels mark untrusted claims, not independent proof."
      • changedInput schema / properties / request / properties / evidence / items / properties / text / description
        Previous value: -"Record content used to assess the answer; payment authorization is not semantic evidence."New value: +"Record content to review; never payment authorization as semantic proof."
      • changedInput schema / properties / request / properties / expected_output / description
        Previous value: -"Optional format directives or correction target; factual text here is not corroborating evidence."New value: +"Optional format/constraint and repair-target context for all operations, including Diagnose. Recognized directives (e.g. Return JSON) can affect diagnosis. Factual text is not compared for string equality or trusted as evidence; supply independent records."
      • changedInput schema / properties / request / properties / schema / description
        Previous value: -"Exact FAHCE request contract identifier."New value: +"Request contract identifier; use this exact value."
    • Changedfahce_verify_repaired_output12 fields changed
      • removedInput schema / examples
        Removed value: -[
-  {
-    "request": {
-      "candidate_output": "Deployment failed.",
-      "evidence": [
-        {
-          "id": "deployment_log",
-          "kind": "log",
-          "source_label": "independent deployment log",
-          "text": "Deployment failed."
-        }
-      ],
-      "schema": "FAHCE_MACHINE_REQUEST_V1"
-    }
-  }
-]
      • changedInput schema / properties / idempotency_key / description
        Previous value: -"Optional REST Idempotency-Key. Reuse only with unchanged operation, input, and authorization; recover saved results after uncertain delivery."New value: +"Optional REST Idempotency-Key; bind unchanged operation, input and authorization. Reuse conflicts on changes; recover saved results instead of paying again."
      • changedInput schema / properties / request / description
        Previous value: -"Answer and supporting records for REST review. Whole request: 524288 UTF-8 bytes including the MCP wrapper; character limits use UTF-16 code units."New value: +"Send this request object alone to the paid REST endpoint. Entire JSON must fit 524288 UTF-8 bytes, including MCP wrapper, labels and escaping; per-field ceilings cannot all be used together. Character limits use UTF-16 code units."
      • changedInput schema / properties / request / properties / candidate_output / description
        Previous value: -"Answer to diagnose, correct, or recheck; for Verify, supply the revised answer."New value: +"The exact candidate output to diagnose or verify. Never use payment evidence as semantic evidence."
      • changedInput schema / properties / request / properties / evidence / description
        Previous value: -"Up to 12 caller-supplied records. No sources are fetched or authenticated; an empty list provides no corroboration."New value: +"Caller-supplied records; sources are not authenticated or fetched. An empty array supplies no corroboration."
      • changedInput schema / properties / request / properties / evidence / items / properties / claim_bearing / description
        Previous value: -"True treats this record as claims to check. False or omission does not override candidate-source labels."New value: +"True marks candidate claims, not corroboration. False or omission does not override candidate-source labels."
      • changedInput schema / properties / request / properties / evidence / items / properties / id / description
        Previous value: -"Unique evidence reference within this request, such as deployment_log."New value: +"Unique evidence identifier within this request."
      • changedInput schema / properties / request / properties / evidence / items / properties / kind / description
        Previous value: -"How this record is represented: log, pasted text, document, or description; this does not set its trust level."New value: +"Record format category, not a trust level."
      • changedInput schema / properties / request / properties / evidence / items / properties / source_label / description
        Previous value: -"Record attribution, such as deployment log; candidate/output labels identify claims rather than independent corroboration."New value: +"Source attribution; candidate/output labels mark untrusted claims, not independent proof."
      • changedInput schema / properties / request / properties / evidence / items / properties / text / description
        Previous value: -"Record content used to assess the answer; payment authorization is not semantic evidence."New value: +"Record content to review; never payment authorization as semantic proof."
      • changedInput schema / properties / request / properties / expected_output / description
        Previous value: -"Optional format directives or correction target; factual text here is not corroborating evidence."New value: +"Optional format/constraint and repair-target context for all operations, including Diagnose. Recognized directives (e.g. Return JSON) can affect diagnosis. Factual text is not compared for string equality or trusted as evidence; supply independent records."
      • changedInput schema / properties / request / properties / schema / description
        Previous value: -"Exact FAHCE request contract identifier."New value: +"Request contract identifier; use this exact value."
  4. 4 tool updates
    • Changedfahce_diagnose_integrity12 fields changed
      • addedInput schema / examples
        Added value: +[
+  {
+    "request": {
+      "candidate_output": "Deployment completed successfully.",
+      "evidence": [
+        {
+          "id": "deployment_log",
+          "kind": "log",
+          "source_label": "independent deployment log",
+          "text": "Deployment failed."
+        }
+      ],
+      "schema": "FAHCE_MACHINE_REQUEST_V1"
+    }
+  }
+]
      • changedInput schema / properties / idempotency_key / description
        Previous value: -"Optional REST Idempotency-Key; bind unchanged operation, input and authorization. Reuse conflicts on changes; recover saved results instead of paying again."New value: +"Optional REST Idempotency-Key. Reuse only with unchanged operation, input, and authorization; recover saved results after uncertain delivery."
      • changedInput schema / properties / request / description
        Previous value: -"Send this request object alone to the paid REST endpoint. Entire JSON must fit 524288 UTF-8 bytes, including MCP wrapper, labels and escaping; per-field ceilings cannot all be used together. Character limits use UTF-16 code units."New value: +"Answer and supporting records for REST review. Whole request: 524288 UTF-8 bytes including the MCP wrapper; character limits use UTF-16 code units."
      • changedInput schema / properties / request / properties / candidate_output / description
        Previous value: -"The exact candidate output to diagnose or verify. Never use payment evidence as semantic evidence."New value: +"Answer to diagnose, correct, or recheck; for Verify, supply the revised answer."
      • changedInput schema / properties / request / properties / evidence / description
        Previous value: -"Caller-supplied records; sources are not authenticated or fetched. An empty array supplies no corroboration."New value: +"Up to 12 caller-supplied records. No sources are fetched or authenticated; an empty list provides no corroboration."
      • changedInput schema / properties / request / properties / evidence / items / properties / claim_bearing / description
        Previous value: -"True marks candidate claims, not corroboration. False or omission does not override candidate-source labels."New value: +"True treats this record as claims to check. False or omission does not override candidate-source labels."
      • changedInput schema / properties / request / properties / evidence / items / properties / id / description
        Previous value: -"Unique evidence identifier within this request."New value: +"Unique evidence reference within this request, such as deployment_log."
      • changedInput schema / properties / request / properties / evidence / items / properties / kind / description
        Previous value: -"Record format category, not a trust level."New value: +"How this record is represented: log, pasted text, document, or description; this does not set its trust level."
      • changedInput schema / properties / request / properties / evidence / items / properties / source_label / description
        Previous value: -"Source attribution; candidate/output labels mark untrusted claims, not independent proof."New value: +"Record attribution, such as deployment log; candidate/output labels identify claims rather than independent corroboration."
      • changedInput schema / properties / request / properties / evidence / items / properties / text / description
        Previous value: -"Record content to review; never payment authorization as semantic proof."New value: +"Record content used to assess the answer; payment authorization is not semantic evidence."
      • changedInput schema / properties / request / properties / expected_output / description
        Previous value: -"Optional format/constraint and repair-target context for all operations, including Diagnose. Recognized directives (e.g. Return JSON) can affect diagnosis. Factual text is not compared for string equality or trusted as evidence; supply independent records."New value: +"Optional format directives or correction target; factual text here is not corroborating evidence."
      • changedInput schema / properties / request / properties / schema / description
        Previous value: -"Request contract identifier; use this exact value."New value: +"Exact FAHCE request contract identifier."
    • Changedfahce_integrity_repair_bundle12 fields changed
      • addedInput schema / examples
        Added value: +[
+  {
+    "request": {
+      "candidate_output": "Deployment completed successfully.",
+      "evidence": [
+        {
+          "id": "deployment_log",
+          "kind": "log",
+          "source_label": "independent deployment log",
+          "text": "Deployment failed."
+        }
+      ],
+      "schema": "FAHCE_MACHINE_REQUEST_V1"
+    }
+  }
+]
      • changedInput schema / properties / idempotency_key / description
        Previous value: -"Optional REST Idempotency-Key; bind unchanged operation, input and authorization. Reuse conflicts on changes; recover saved results instead of paying again."New value: +"Optional REST Idempotency-Key. Reuse only with unchanged operation, input, and authorization; recover saved results after uncertain delivery."
      • changedInput schema / properties / request / description
        Previous value: -"Send this request object alone to the paid REST endpoint. Entire JSON must fit 524288 UTF-8 bytes, including MCP wrapper, labels and escaping; per-field ceilings cannot all be used together. Character limits use UTF-16 code units."New value: +"Answer and supporting records for REST review. Whole request: 524288 UTF-8 bytes including the MCP wrapper; character limits use UTF-16 code units."
      • changedInput schema / properties / request / properties / candidate_output / description
        Previous value: -"The exact candidate output to diagnose or verify. Never use payment evidence as semantic evidence."New value: +"Answer to diagnose, correct, or recheck; for Verify, supply the revised answer."
      • changedInput schema / properties / request / properties / evidence / description
        Previous value: -"Caller-supplied records; sources are not authenticated or fetched. An empty array supplies no corroboration."New value: +"Up to 12 caller-supplied records. No sources are fetched or authenticated; an empty list provides no corroboration."
      • changedInput schema / properties / request / properties / evidence / items / properties / claim_bearing / description
        Previous value: -"True marks candidate claims, not corroboration. False or omission does not override candidate-source labels."New value: +"True treats this record as claims to check. False or omission does not override candidate-source labels."
      • changedInput schema / properties / request / properties / evidence / items / properties / id / description
        Previous value: -"Unique evidence identifier within this request."New value: +"Unique evidence reference within this request, such as deployment_log."
      • changedInput schema / properties / request / properties / evidence / items / properties / kind / description
        Previous value: -"Record format category, not a trust level."New value: +"How this record is represented: log, pasted text, document, or description; this does not set its trust level."
      • changedInput schema / properties / request / properties / evidence / items / properties / source_label / description
        Previous value: -"Source attribution; candidate/output labels mark untrusted claims, not independent proof."New value: +"Record attribution, such as deployment log; candidate/output labels identify claims rather than independent corroboration."
      • changedInput schema / properties / request / properties / evidence / items / properties / text / description
        Previous value: -"Record content to review; never payment authorization as semantic proof."New value: +"Record content used to assess the answer; payment authorization is not semantic evidence."
      • changedInput schema / properties / request / properties / expected_output / description
        Previous value: -"Optional format/constraint and repair-target context for all operations, including Diagnose. Recognized directives (e.g. Return JSON) can affect diagnosis. Factual text is not compared for string equality or trusted as evidence; supply independent records."New value: +"Optional format directives or correction target; factual text here is not corroborating evidence."
      • changedInput schema / properties / request / properties / schema / description
        Previous value: -"Request contract identifier; use this exact value."New value: +"Exact FAHCE request contract identifier."
    • Changedfahce_plan_bounded_repair12 fields changed
      • addedInput schema / examples
        Added value: +[
+  {
+    "request": {
+      "candidate_output": "Deployment completed successfully.",
+      "evidence": [
+        {
+          "id": "deployment_log",
+          "kind": "log",
+          "source_label": "independent deployment log",
+          "text": "Deployment failed."
+        }
+      ],
+      "schema": "FAHCE_MACHINE_REQUEST_V1"
+    }
+  }
+]
      • changedInput schema / properties / idempotency_key / description
        Previous value: -"Optional REST Idempotency-Key; bind unchanged operation, input and authorization. Reuse conflicts on changes; recover saved results instead of paying again."New value: +"Optional REST Idempotency-Key. Reuse only with unchanged operation, input, and authorization; recover saved results after uncertain delivery."
      • changedInput schema / properties / request / description
        Previous value: -"Send this request object alone to the paid REST endpoint. Entire JSON must fit 524288 UTF-8 bytes, including MCP wrapper, labels and escaping; per-field ceilings cannot all be used together. Character limits use UTF-16 code units."New value: +"Answer and supporting records for REST review. Whole request: 524288 UTF-8 bytes including the MCP wrapper; character limits use UTF-16 code units."
      • changedInput schema / properties / request / properties / candidate_output / description
        Previous value: -"The exact candidate output to diagnose or verify. Never use payment evidence as semantic evidence."New value: +"Answer to diagnose, correct, or recheck; for Verify, supply the revised answer."
      • changedInput schema / properties / request / properties / evidence / description
        Previous value: -"Caller-supplied records; sources are not authenticated or fetched. An empty array supplies no corroboration."New value: +"Up to 12 caller-supplied records. No sources are fetched or authenticated; an empty list provides no corroboration."
      • changedInput schema / properties / request / properties / evidence / items / properties / claim_bearing / description
        Previous value: -"True marks candidate claims, not corroboration. False or omission does not override candidate-source labels."New value: +"True treats this record as claims to check. False or omission does not override candidate-source labels."
      • changedInput schema / properties / request / properties / evidence / items / properties / id / description
        Previous value: -"Unique evidence identifier within this request."New value: +"Unique evidence reference within this request, such as deployment_log."
      • changedInput schema / properties / request / properties / evidence / items / properties / kind / description
        Previous value: -"Record format category, not a trust level."New value: +"How this record is represented: log, pasted text, document, or description; this does not set its trust level."
      • changedInput schema / properties / request / properties / evidence / items / properties / source_label / description
        Previous value: -"Source attribution; candidate/output labels mark untrusted claims, not independent proof."New value: +"Record attribution, such as deployment log; candidate/output labels identify claims rather than independent corroboration."
      • changedInput schema / properties / request / properties / evidence / items / properties / text / description
        Previous value: -"Record content to review; never payment authorization as semantic proof."New value: +"Record content used to assess the answer; payment authorization is not semantic evidence."
      • changedInput schema / properties / request / properties / expected_output / description
        Previous value: -"Optional format/constraint and repair-target context for all operations, including Diagnose. Recognized directives (e.g. Return JSON) can affect diagnosis. Factual text is not compared for string equality or trusted as evidence; supply independent records."New value: +"Optional format directives or correction target; factual text here is not corroborating evidence."
      • changedInput schema / properties / request / properties / schema / description
        Previous value: -"Request contract identifier; use this exact value."New value: +"Exact FAHCE request contract identifier."
    • Changedfahce_verify_repaired_output12 fields changed
      • addedInput schema / examples
        Added value: +[
+  {
+    "request": {
+      "candidate_output": "Deployment failed.",
+      "evidence": [
+        {
+          "id": "deployment_log",
+          "kind": "log",
+          "source_label": "independent deployment log",
+          "text": "Deployment failed."
+        }
+      ],
+      "schema": "FAHCE_MACHINE_REQUEST_V1"
+    }
+  }
+]
      • changedInput schema / properties / idempotency_key / description
        Previous value: -"Optional REST Idempotency-Key; bind unchanged operation, input and authorization. Reuse conflicts on changes; recover saved results instead of paying again."New value: +"Optional REST Idempotency-Key. Reuse only with unchanged operation, input, and authorization; recover saved results after uncertain delivery."
      • changedInput schema / properties / request / description
        Previous value: -"Send this request object alone to the paid REST endpoint. Entire JSON must fit 524288 UTF-8 bytes, including MCP wrapper, labels and escaping; per-field ceilings cannot all be used together. Character limits use UTF-16 code units."New value: +"Answer and supporting records for REST review. Whole request: 524288 UTF-8 bytes including the MCP wrapper; character limits use UTF-16 code units."
      • changedInput schema / properties / request / properties / candidate_output / description
        Previous value: -"The exact candidate output to diagnose or verify. Never use payment evidence as semantic evidence."New value: +"Answer to diagnose, correct, or recheck; for Verify, supply the revised answer."
      • changedInput schema / properties / request / properties / evidence / description
        Previous value: -"Caller-supplied records; sources are not authenticated or fetched. An empty array supplies no corroboration."New value: +"Up to 12 caller-supplied records. No sources are fetched or authenticated; an empty list provides no corroboration."
      • changedInput schema / properties / request / properties / evidence / items / properties / claim_bearing / description
        Previous value: -"True marks candidate claims, not corroboration. False or omission does not override candidate-source labels."New value: +"True treats this record as claims to check. False or omission does not override candidate-source labels."
      • changedInput schema / properties / request / properties / evidence / items / properties / id / description
        Previous value: -"Unique evidence identifier within this request."New value: +"Unique evidence reference within this request, such as deployment_log."
      • changedInput schema / properties / request / properties / evidence / items / properties / kind / description
        Previous value: -"Record format category, not a trust level."New value: +"How this record is represented: log, pasted text, document, or description; this does not set its trust level."
      • changedInput schema / properties / request / properties / evidence / items / properties / source_label / description
        Previous value: -"Source attribution; candidate/output labels mark untrusted claims, not independent proof."New value: +"Record attribution, such as deployment log; candidate/output labels identify claims rather than independent corroboration."
      • changedInput schema / properties / request / properties / evidence / items / properties / text / description
        Previous value: -"Record content to review; never payment authorization as semantic proof."New value: +"Record content used to assess the answer; payment authorization is not semantic evidence."
      • changedInput schema / properties / request / properties / expected_output / description
        Previous value: -"Optional format/constraint and repair-target context for all operations, including Diagnose. Recognized directives (e.g. Return JSON) can affect diagnosis. Factual text is not compared for string equality or trusted as evidence; supply independent records."New value: +"Optional format directives or correction target; factual text here is not corroborating evidence."
      • changedInput schema / properties / request / properties / schema / description
        Previous value: -"Request contract identifier; use this exact value."New value: +"Exact FAHCE request contract identifier."
  5. 4 tool updates
    • Changedfahce_diagnose_integrity4 fields changed
      • addedOutput schema / allOf
        Added value: +[
+  {
+    "if": {
+      "properties": {
+        "receipt": {
+          "properties": {
+            "response_hash_scheme": {
+              "const": "SHA256_SORTED_JSON_RESPONSE_WITHOUT_ATTESTATION_V3"
+            }
+          },
+          "required": [
+            "response_hash_scheme"
+          ]
+        }
+      },
+      "required": [
+        "receipt"
+      ]
+    },
+    "then": {
+      "required": [
+        "attestation"
+      ]
+    }
+  }
+]
      • addedOutput schema / properties / attestation
        Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "binding": {
+      "properties": {
+        "engine_version": {
+          "type": "string"
+        },
+        "input_hash": {
+          "type": "string"
+        },
+        "issued_at": {
+          "type": "integer"
+        },
+        "nonce": {
+          "type": "string"
+        },
+        "request_id": {
+          "type": "string"
+        },
+        "response_hash": {
+          "type": "string"
+        },
+        "schema": {
+          "const": "FAHCE_MACHINE_RESULT_BINDING_V1"
+        },
+        "scope": {
+          "const": "CONFIDENTIAL_DETERMINISTIC_COMPUTATION"
+        }
+      },
+      "required": [
+        "schema",
+        "nonce",
+        "request_id",
+        "input_hash",
+        "response_hash",
+        "engine_version",
+        "issued_at",
+        "scope"
+      ],
+      "type": "object"
+    },
+    "maa_token": {
+      "description": "Microsoft-signed MAA JWT; verify against the published trust material and exact response binding.",
+      "type": "string"
+    },
+    "policy_sha256": {
+      "pattern": "^[a-f0-9]{64}$",
+      "type": "string"
+    },
+    "schema": {
+      "const": "FAHCE_MACHINE_ATTESTATION_V1"
+    }
+  },
+  "required": [
+    "schema",
+    "policy_sha256",
+    "binding",
+    "maa_token"
+  ],
+  "type": "object"
+}
      • changedOutput schema / properties / receipt / properties / hash_scheme / enum
        Previous value: -[
-  "SHA256_CANONICAL_JSON_RESULT_WITH_EMPTY_RESULT_HASH_V1",
-  "SHA256_SORTED_JSON_RESULT_WITH_EMPTY_RESULT_HASH_V2"
-]New value: +[
+  "SHA256_CANONICAL_JSON_RESULT_WITH_EMPTY_RESULT_HASH_V1",
+  "SHA256_SORTED_JSON_RESULT_WITH_EMPTY_RESULT_HASH_V2",
+  "SHA256_SORTED_JSON_RESULT_WITHOUT_ATTESTATION_V3"
+]
      • changedOutput schema / properties / receipt / properties / response_hash_scheme / enum
        Previous value: -[
-  "SHA256_JSON_RESPONSE_WITH_EMPTY_RESPONSE_HASH_V1",
-  "SHA256_SORTED_JSON_RESPONSE_WITH_EMPTY_RESPONSE_HASH_V2"
-]New value: +[
+  "SHA256_JSON_RESPONSE_WITH_EMPTY_RESPONSE_HASH_V1",
+  "SHA256_SORTED_JSON_RESPONSE_WITH_EMPTY_RESPONSE_HASH_V2",
+  "SHA256_SORTED_JSON_RESPONSE_WITHOUT_ATTESTATION_V3"
+]
    • Changedfahce_integrity_repair_bundle4 fields changed
      • addedOutput schema / allOf
        Added value: +[
+  {
+    "if": {
+      "properties": {
+        "receipt": {
+          "properties": {
+            "response_hash_scheme": {
+              "const": "SHA256_SORTED_JSON_RESPONSE_WITHOUT_ATTESTATION_V3"
+            }
+          },
+          "required": [
+            "response_hash_scheme"
+          ]
+        }
+      },
+      "required": [
+        "receipt"
+      ]
+    },
+    "then": {
+      "required": [
+        "attestation"
+      ]
+    }
+  }
+]
      • addedOutput schema / properties / attestation
        Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "binding": {
+      "properties": {
+        "engine_version": {
+          "type": "string"
+        },
+        "input_hash": {
+          "type": "string"
+        },
+        "issued_at": {
+          "type": "integer"
+        },
+        "nonce": {
+          "type": "string"
+        },
+        "request_id": {
+          "type": "string"
+        },
+        "response_hash": {
+          "type": "string"
+        },
+        "schema": {
+          "const": "FAHCE_MACHINE_RESULT_BINDING_V1"
+        },
+        "scope": {
+          "const": "CONFIDENTIAL_DETERMINISTIC_COMPUTATION"
+        }
+      },
+      "required": [
+        "schema",
+        "nonce",
+        "request_id",
+        "input_hash",
+        "response_hash",
+        "engine_version",
+        "issued_at",
+        "scope"
+      ],
+      "type": "object"
+    },
+    "maa_token": {
+      "description": "Microsoft-signed MAA JWT; verify against the published trust material and exact response binding.",
+      "type": "string"
+    },
+    "policy_sha256": {
+      "pattern": "^[a-f0-9]{64}$",
+      "type": "string"
+    },
+    "schema": {
+      "const": "FAHCE_MACHINE_ATTESTATION_V1"
+    }
+  },
+  "required": [
+    "schema",
+    "policy_sha256",
+    "binding",
+    "maa_token"
+  ],
+  "type": "object"
+}
      • changedOutput schema / properties / receipt / properties / hash_scheme / enum
        Previous value: -[
-  "SHA256_CANONICAL_JSON_RESULT_WITH_EMPTY_RESULT_HASH_V1",
-  "SHA256_SORTED_JSON_RESULT_WITH_EMPTY_RESULT_HASH_V2"
-]New value: +[
+  "SHA256_CANONICAL_JSON_RESULT_WITH_EMPTY_RESULT_HASH_V1",
+  "SHA256_SORTED_JSON_RESULT_WITH_EMPTY_RESULT_HASH_V2",
+  "SHA256_SORTED_JSON_RESULT_WITHOUT_ATTESTATION_V3"
+]
      • changedOutput schema / properties / receipt / properties / response_hash_scheme / enum
        Previous value: -[
-  "SHA256_JSON_RESPONSE_WITH_EMPTY_RESPONSE_HASH_V1",
-  "SHA256_SORTED_JSON_RESPONSE_WITH_EMPTY_RESPONSE_HASH_V2"
-]New value: +[
+  "SHA256_JSON_RESPONSE_WITH_EMPTY_RESPONSE_HASH_V1",
+  "SHA256_SORTED_JSON_RESPONSE_WITH_EMPTY_RESPONSE_HASH_V2",
+  "SHA256_SORTED_JSON_RESPONSE_WITHOUT_ATTESTATION_V3"
+]
    • Changedfahce_plan_bounded_repair4 fields changed
      • addedOutput schema / allOf
        Added value: +[
+  {
+    "if": {
+      "properties": {
+        "receipt": {
+          "properties": {
+            "response_hash_scheme": {
+              "const": "SHA256_SORTED_JSON_RESPONSE_WITHOUT_ATTESTATION_V3"
+            }
+          },
+          "required": [
+            "response_hash_scheme"
+          ]
+        }
+      },
+      "required": [
+        "receipt"
+      ]
+    },
+    "then": {
+      "required": [
+        "attestation"
+      ]
+    }
+  }
+]
      • addedOutput schema / properties / attestation
        Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "binding": {
+      "properties": {
+        "engine_version": {
+          "type": "string"
+        },
+        "input_hash": {
+          "type": "string"
+        },
+        "issued_at": {
+          "type": "integer"
+        },
+        "nonce": {
+          "type": "string"
+        },
+        "request_id": {
+          "type": "string"
+        },
+        "response_hash": {
+          "type": "string"
+        },
+        "schema": {
+          "const": "FAHCE_MACHINE_RESULT_BINDING_V1"
+        },
+        "scope": {
+          "const": "CONFIDENTIAL_DETERMINISTIC_COMPUTATION"
+        }
+      },
+      "required": [
+        "schema",
+        "nonce",
+        "request_id",
+        "input_hash",
+        "response_hash",
+        "engine_version",
+        "issued_at",
+        "scope"
+      ],
+      "type": "object"
+    },
+    "maa_token": {
+      "description": "Microsoft-signed MAA JWT; verify against the published trust material and exact response binding.",
+      "type": "string"
+    },
+    "policy_sha256": {
+      "pattern": "^[a-f0-9]{64}$",
+      "type": "string"
+    },
+    "schema": {
+      "const": "FAHCE_MACHINE_ATTESTATION_V1"
+    }
+  },
+  "required": [
+    "schema",
+    "policy_sha256",
+    "binding",
+    "maa_token"
+  ],
+  "type": "object"
+}
      • changedOutput schema / properties / receipt / properties / hash_scheme / enum
        Previous value: -[
-  "SHA256_CANONICAL_JSON_RESULT_WITH_EMPTY_RESULT_HASH_V1",
-  "SHA256_SORTED_JSON_RESULT_WITH_EMPTY_RESULT_HASH_V2"
-]New value: +[
+  "SHA256_CANONICAL_JSON_RESULT_WITH_EMPTY_RESULT_HASH_V1",
+  "SHA256_SORTED_JSON_RESULT_WITH_EMPTY_RESULT_HASH_V2",
+  "SHA256_SORTED_JSON_RESULT_WITHOUT_ATTESTATION_V3"
+]
      • changedOutput schema / properties / receipt / properties / response_hash_scheme / enum
        Previous value: -[
-  "SHA256_JSON_RESPONSE_WITH_EMPTY_RESPONSE_HASH_V1",
-  "SHA256_SORTED_JSON_RESPONSE_WITH_EMPTY_RESPONSE_HASH_V2"
-]New value: +[
+  "SHA256_JSON_RESPONSE_WITH_EMPTY_RESPONSE_HASH_V1",
+  "SHA256_SORTED_JSON_RESPONSE_WITH_EMPTY_RESPONSE_HASH_V2",
+  "SHA256_SORTED_JSON_RESPONSE_WITHOUT_ATTESTATION_V3"
+]
    • Changedfahce_verify_repaired_output4 fields changed
      • addedOutput schema / allOf
        Added value: +[
+  {
+    "if": {
+      "properties": {
+        "receipt": {
+          "properties": {
+            "response_hash_scheme": {
+              "const": "SHA256_SORTED_JSON_RESPONSE_WITHOUT_ATTESTATION_V3"
+            }
+          },
+          "required": [
+            "response_hash_scheme"
+          ]
+        }
+      },
+      "required": [
+        "receipt"
+      ]
+    },
+    "then": {
+      "required": [
+        "attestation"
+      ]
+    }
+  }
+]
      • addedOutput schema / properties / attestation
        Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "binding": {
+      "properties": {
+        "engine_version": {
+          "type": "string"
+        },
+        "input_hash": {
+          "type": "string"
+        },
+        "issued_at": {
+          "type": "integer"
+        },
+        "nonce": {
+          "type": "string"
+        },
+        "request_id": {
+          "type": "string"
+        },
+        "response_hash": {
+          "type": "string"
+        },
+        "schema": {
+          "const": "FAHCE_MACHINE_RESULT_BINDING_V1"
+        },
+        "scope": {
+          "const": "CONFIDENTIAL_DETERMINISTIC_COMPUTATION"
+        }
+      },
+      "required": [
+        "schema",
+        "nonce",
+        "request_id",
+        "input_hash",
+        "response_hash",
+        "engine_version",
+        "issued_at",
+        "scope"
+      ],
+      "type": "object"
+    },
+    "maa_token": {
+      "description": "Microsoft-signed MAA JWT; verify against the published trust material and exact response binding.",
+      "type": "string"
+    },
+    "policy_sha256": {
+      "pattern": "^[a-f0-9]{64}$",
+      "type": "string"
+    },
+    "schema": {
+      "const": "FAHCE_MACHINE_ATTESTATION_V1"
+    }
+  },
+  "required": [
+    "schema",
+    "policy_sha256",
+    "binding",
+    "maa_token"
+  ],
+  "type": "object"
+}
      • changedOutput schema / properties / receipt / properties / hash_scheme / enum
        Previous value: -[
-  "SHA256_CANONICAL_JSON_RESULT_WITH_EMPTY_RESULT_HASH_V1",
-  "SHA256_SORTED_JSON_RESULT_WITH_EMPTY_RESULT_HASH_V2"
-]New value: +[
+  "SHA256_CANONICAL_JSON_RESULT_WITH_EMPTY_RESULT_HASH_V1",
+  "SHA256_SORTED_JSON_RESULT_WITH_EMPTY_RESULT_HASH_V2",
+  "SHA256_SORTED_JSON_RESULT_WITHOUT_ATTESTATION_V3"
+]
      • changedOutput schema / properties / receipt / properties / response_hash_scheme / enum
        Previous value: -[
-  "SHA256_JSON_RESPONSE_WITH_EMPTY_RESPONSE_HASH_V1",
-  "SHA256_SORTED_JSON_RESPONSE_WITH_EMPTY_RESPONSE_HASH_V2"
-]New value: +[
+  "SHA256_JSON_RESPONSE_WITH_EMPTY_RESPONSE_HASH_V1",
+  "SHA256_SORTED_JSON_RESPONSE_WITH_EMPTY_RESPONSE_HASH_V2",
+  "SHA256_SORTED_JSON_RESPONSE_WITHOUT_ATTESTATION_V3"
+]
  6. 4 tool updates
    • Changedfahce_diagnose_integrity10 fields changed
      • addedInput schema / properties / idempotency_key / description
        Added value: +"Optional REST Idempotency-Key; bind unchanged operation, input and authorization. Reuse conflicts on changes; recover saved results instead of paying again."
      • changedInput schema / properties / request / description
        Previous value: -"The entire UTF-8 encoded JSON body must fit within 524288 bytes (512 KiB), including all fields, labels, escaping and JSON overhead. Per-field maxima are independent ceilings; they cannot all be used at once. MCP includes its JSON-RPC wrapper in the same body ceiling. Character limits are UTF-16 code units."New value: +"Send this request object alone to the paid REST endpoint. Entire JSON must fit 524288 UTF-8 bytes, including MCP wrapper, labels and escaping; per-field ceilings cannot all be used together. Character limits use UTF-16 code units."
      • addedInput schema / properties / request / properties / evidence / description
        Added value: +"Caller-supplied records; sources are not authenticated or fetched. An empty array supplies no corroboration."
      • addedInput schema / properties / request / properties / evidence / items / properties / claim_bearing / description
        Added value: +"True marks candidate claims, not corroboration. False or omission does not override candidate-source labels."
      • addedInput schema / properties / request / properties / evidence / items / properties / id / description
        Added value: +"Unique evidence identifier within this request."
      • addedInput schema / properties / request / properties / evidence / items / properties / kind / description
        Added value: +"Record format category, not a trust level."
      • addedInput schema / properties / request / properties / evidence / items / properties / source_label / description
        Added value: +"Source attribution; candidate/output labels mark untrusted claims, not independent proof."
      • addedInput schema / properties / request / properties / evidence / items / properties / text / description
        Added value: +"Record content to review; never payment authorization as semantic proof."
      • changedInput schema / properties / request / properties / expected_output / description
        Previous value: -"Optional response-contract and repair-target context for all operations, including Diagnose. Supported response-format directives (for example, Return JSON) and implemented explicit constraints can affect the diagnosis. Ordinary matching or mismatching factual text is not compared for string equality and is not a trusted answer oracle or supporting evidence; supply independent evidence for factual claims."New value: +"Optional format/constraint and repair-target context for all operations, including Diagnose. Recognized directives (e.g. Return JSON) can affect diagnosis. Factual text is not compared for string equality or trusted as evidence; supply independent records."
      • addedInput schema / properties / request / properties / schema / description
        Added value: +"Request contract identifier; use this exact value."
    • Changedfahce_integrity_repair_bundle10 fields changed
      • addedInput schema / properties / idempotency_key / description
        Added value: +"Optional REST Idempotency-Key; bind unchanged operation, input and authorization. Reuse conflicts on changes; recover saved results instead of paying again."
      • changedInput schema / properties / request / description
        Previous value: -"The entire UTF-8 encoded JSON body must fit within 524288 bytes (512 KiB), including all fields, labels, escaping and JSON overhead. Per-field maxima are independent ceilings; they cannot all be used at once. MCP includes its JSON-RPC wrapper in the same body ceiling. Character limits are UTF-16 code units."New value: +"Send this request object alone to the paid REST endpoint. Entire JSON must fit 524288 UTF-8 bytes, including MCP wrapper, labels and escaping; per-field ceilings cannot all be used together. Character limits use UTF-16 code units."
      • addedInput schema / properties / request / properties / evidence / description
        Added value: +"Caller-supplied records; sources are not authenticated or fetched. An empty array supplies no corroboration."
      • addedInput schema / properties / request / properties / evidence / items / properties / claim_bearing / description
        Added value: +"True marks candidate claims, not corroboration. False or omission does not override candidate-source labels."
      • addedInput schema / properties / request / properties / evidence / items / properties / id / description
        Added value: +"Unique evidence identifier within this request."
      • addedInput schema / properties / request / properties / evidence / items / properties / kind / description
        Added value: +"Record format category, not a trust level."
      • addedInput schema / properties / request / properties / evidence / items / properties / source_label / description
        Added value: +"Source attribution; candidate/output labels mark untrusted claims, not independent proof."
      • addedInput schema / properties / request / properties / evidence / items / properties / text / description
        Added value: +"Record content to review; never payment authorization as semantic proof."
      • changedInput schema / properties / request / properties / expected_output / description
        Previous value: -"Optional response-contract and repair-target context for all operations, including Diagnose. Supported response-format directives (for example, Return JSON) and implemented explicit constraints can affect the diagnosis. Ordinary matching or mismatching factual text is not compared for string equality and is not a trusted answer oracle or supporting evidence; supply independent evidence for factual claims."New value: +"Optional format/constraint and repair-target context for all operations, including Diagnose. Recognized directives (e.g. Return JSON) can affect diagnosis. Factual text is not compared for string equality or trusted as evidence; supply independent records."
      • addedInput schema / properties / request / properties / schema / description
        Added value: +"Request contract identifier; use this exact value."
    • Changedfahce_plan_bounded_repair10 fields changed
      • addedInput schema / properties / idempotency_key / description
        Added value: +"Optional REST Idempotency-Key; bind unchanged operation, input and authorization. Reuse conflicts on changes; recover saved results instead of paying again."
      • changedInput schema / properties / request / description
        Previous value: -"The entire UTF-8 encoded JSON body must fit within 524288 bytes (512 KiB), including all fields, labels, escaping and JSON overhead. Per-field maxima are independent ceilings; they cannot all be used at once. MCP includes its JSON-RPC wrapper in the same body ceiling. Character limits are UTF-16 code units."New value: +"Send this request object alone to the paid REST endpoint. Entire JSON must fit 524288 UTF-8 bytes, including MCP wrapper, labels and escaping; per-field ceilings cannot all be used together. Character limits use UTF-16 code units."
      • addedInput schema / properties / request / properties / evidence / description
        Added value: +"Caller-supplied records; sources are not authenticated or fetched. An empty array supplies no corroboration."
      • addedInput schema / properties / request / properties / evidence / items / properties / claim_bearing / description
        Added value: +"True marks candidate claims, not corroboration. False or omission does not override candidate-source labels."
      • addedInput schema / properties / request / properties / evidence / items / properties / id / description
        Added value: +"Unique evidence identifier within this request."
      • addedInput schema / properties / request / properties / evidence / items / properties / kind / description
        Added value: +"Record format category, not a trust level."
      • addedInput schema / properties / request / properties / evidence / items / properties / source_label / description
        Added value: +"Source attribution; candidate/output labels mark untrusted claims, not independent proof."
      • addedInput schema / properties / request / properties / evidence / items / properties / text / description
        Added value: +"Record content to review; never payment authorization as semantic proof."
      • changedInput schema / properties / request / properties / expected_output / description
        Previous value: -"Optional response-contract and repair-target context for all operations, including Diagnose. Supported response-format directives (for example, Return JSON) and implemented explicit constraints can affect the diagnosis. Ordinary matching or mismatching factual text is not compared for string equality and is not a trusted answer oracle or supporting evidence; supply independent evidence for factual claims."New value: +"Optional format/constraint and repair-target context for all operations, including Diagnose. Recognized directives (e.g. Return JSON) can affect diagnosis. Factual text is not compared for string equality or trusted as evidence; supply independent records."
      • addedInput schema / properties / request / properties / schema / description
        Added value: +"Request contract identifier; use this exact value."
    • Changedfahce_verify_repaired_output10 fields changed
      • addedInput schema / properties / idempotency_key / description
        Added value: +"Optional REST Idempotency-Key; bind unchanged operation, input and authorization. Reuse conflicts on changes; recover saved results instead of paying again."
      • changedInput schema / properties / request / description
        Previous value: -"The entire UTF-8 encoded JSON body must fit within 524288 bytes (512 KiB), including all fields, labels, escaping and JSON overhead. Per-field maxima are independent ceilings; they cannot all be used at once. MCP includes its JSON-RPC wrapper in the same body ceiling. Character limits are UTF-16 code units."New value: +"Send this request object alone to the paid REST endpoint. Entire JSON must fit 524288 UTF-8 bytes, including MCP wrapper, labels and escaping; per-field ceilings cannot all be used together. Character limits use UTF-16 code units."
      • addedInput schema / properties / request / properties / evidence / description
        Added value: +"Caller-supplied records; sources are not authenticated or fetched. An empty array supplies no corroboration."
      • addedInput schema / properties / request / properties / evidence / items / properties / claim_bearing / description
        Added value: +"True marks candidate claims, not corroboration. False or omission does not override candidate-source labels."
      • addedInput schema / properties / request / properties / evidence / items / properties / id / description
        Added value: +"Unique evidence identifier within this request."
      • addedInput schema / properties / request / properties / evidence / items / properties / kind / description
        Added value: +"Record format category, not a trust level."
      • addedInput schema / properties / request / properties / evidence / items / properties / source_label / description
        Added value: +"Source attribution; candidate/output labels mark untrusted claims, not independent proof."
      • addedInput schema / properties / request / properties / evidence / items / properties / text / description
        Added value: +"Record content to review; never payment authorization as semantic proof."
      • changedInput schema / properties / request / properties / expected_output / description
        Previous value: -"Optional response-contract and repair-target context for all operations, including Diagnose. Supported response-format directives (for example, Return JSON) and implemented explicit constraints can affect the diagnosis. Ordinary matching or mismatching factual text is not compared for string equality and is not a trusted answer oracle or supporting evidence; supply independent evidence for factual claims."New value: +"Optional format/constraint and repair-target context for all operations, including Diagnose. Recognized directives (e.g. Return JSON) can affect diagnosis. Factual text is not compared for string equality or trusted as evidence; supply independent records."
      • addedInput schema / properties / request / properties / schema / description
        Added value: +"Request contract identifier; use this exact value."
  7. 4 tool updates
    • First observedfahce_diagnose_integrity
    • First observedfahce_integrity_repair_bundle
    • First observedfahce_plan_bounded_repair
    • First observedfahce_verify_repaired_output

Related MCP Connectors

Related MCP Servers

  • till

    bzdmin
    A
    license
    Not graded
    quality
    B
    maintenance
    Lets agents discover, verify, and inspect x402/B402 payment endpoints on BNB Chain, with read-only tools to list skills, check live counter behavior, and review the settlement tape.
    5 npm
    MIT

  • address-intel-api

    TKtokyo
    F
    license
    Not graded
    quality
    F
    maintenance
    Provides counterparty risk checks for any EVM address, returning malicious-history flags, tiered risk scoring, and plain-language summaries via x402 payment.
    -

  • scry-mcp

    pfeilisolana
    A
    license
    Not graded
    quality
    B
    maintenance
    A keyless, custody-free MCP server that bridges AI agents to Scry Solana wallet intelligence, paid per request via x402. It provides free discovery tools and brokers paid evidence endpoints, allowing agents to settle payments directly with their own wallets.
    78 npm
    MIT

  • OceanAlt AML (archived, moved)

    OceanAlt
    A
    license
    Not graded
    quality
    F
    maintenance
    Archived and no longer maintained. Tools and prices shown here are out of date. Use the maintained server: glama.ai/mcp/servers/OceanAlt666/oceanalt-aml-mcp (GitHub: OceanAlt666/oceanalt-aml-mcp).
    115 npm
    MIT
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources