Skip to main content
Glama

Trooth

by io.github.troothllc
OverviewDiscussionsAdmin

Server Details

Trooth is an infrastructure and cybersecurity company providing Machine-Readable Trust.

If you are the author of this connector, you can claim ownership with GitHub, an HTTP challenge, or a DNS record. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Last Tested
Transport
Streamable HTTP · MCP 2025-06-18
URL
Repository
troothllc/trooth-mcp
GitHub Stars
0
Server Listing
Trooth Network

TDQS

A4.4/5.0

Scored across 4 tools

Disambiguation5/5

Each tool targets a clearly distinct function: internal knowledge, external site observation, company record reading, and token verification. The descriptions explicitly cross-reference each other (e.g., trooth_ask points to trooth_public_trust_profile) to prevent misselection.

Naming Consistency3/5

All tools share the 'trooth_' prefix, which aids recognition, but the second part is inconsistent: some are verbs (ask, verify), one is an unusual inversion (outside_in_read), and one is a noun phrase (public_trust_profile). The pattern is readable but not uniform.

Tool Count5/5

Four tools is well-scoped for a specialized read/verification server. Each tool serves a distinct purpose and there is no obvious redundancy or bloat.

Completeness4/5

The tool surface covers the main read-only operations: self-knowledge, external security observation, company profile lookup, and token verification. Minor gaps exist (e.g., no way to search or list company records), but the core workflow appears complete for its intended read-only trust-verification role.

Available Tools

4 tools
trooth_askA
Read-onlyIdempotent
Inspect

Answer a question about Trooth itself (what the Trooth Network is, what one company record carries, pricing, how witnessing works) from Trooth's fixed, curated knowledge base. Makes no outside request. A question the knowledge base does not cover returns out_of_scope; for a company's record use trooth_public_trust_profile.

ParametersJSON Schema
NameRequiredDescriptionDefault
questionYesA question about Trooth

Output Schema

ParametersJSON Schema
NameRequiredDescription
statusYesMachine-branchable outcome for this lookup.
subjectYesThe company, domain or token this answer is about.
summaryYesThe same answer as the text content, for display.
evidenceNoPresent on a published profile. What this answer is built from, what it leaves out, and where to get the rest. The summary is a summary: the typed facts with their provenance are in the record at full_record.
claim_urlNoPresent when the subject has no published record (unclaimed or private).
provenanceYesWhere this answer came from. An honest_absence is missing data, never a judgment about the subject. A read_failed means Trooth could not read its own record at this moment and asserts nothing either way; retry rather than concluding. witnessed_reading: a published profile whose reading Trooth witnessed; the profile is not signed, and the one signed object is the reading's witness statement (see evidence.signed_artifact). connected_system_reads: read from systems the company connected. ledger_token_signatures: the result of checking a Trust Ledger Token's two signatures; the claims inside it stay the company's. witnessed_signed is DEPRECATED since 2026-09-26 and no longer returned; it meant any of the three above.

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds valuable context beyond those: 'Makes no outside request,' 'fixed, curated knowledge base,' and the explicit out_of_scope return for uncovered questions. This clarifies the tool's operational boundaries without contradicting annotations.

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?

Three tightly written sentences front-load the core purpose and scope, then add the key behavioral note and sibling routing. Every sentence earns its place with no repetition or filler.

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

Completeness5/5

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

Given the single parameter, rich annotations, and presence of an output schema, the description fully covers what the tool does, when to use it, what it returns for out-of-scope questions, and how it differs from a sibling. Nothing an agent needs to invoke it correctly is missing.

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

Parameters4/5

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

Schema coverage is 100% and the parameter is a simple required string described as 'A question about Trooth.' The description adds meaning by scoping the question to Trooth's knowledge base and specifying the out_of_scope behavior, which helps the agent craft valid inputs. It stops short of giving example phrasings, but the added context is sufficient.

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

Purpose5/5

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

The description uses a specific verb ('Answer a question about Trooth itself') and identifies the resource (Trooth's fixed, curated knowledge base). It enumerates example topics and explicitly contrasts with trooth_public_trust_profile, so an agent can distinguish it from siblings.

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

Usage Guidelines5/5

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

It clearly states when to use the tool: for questions about Trooth itself, not about a company's record. It names the alternative trooth_public_trust_profile for company records and explains the out_of_scope return behavior, giving the agent actionable selection criteria.

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

trooth_outside_in_readA
Read-onlyIdempotent
Inspect

Fetch https:/// and /.well-known/security.txt once, when called, from Trooth's server and report whether HTTPS answered, which of five response headers (HSTS, CSP, nosniff, frame protection, referrer policy) are present, and whether security.txt is published, absent or unread. IP literals and names resolving to private, loopback or link-local addresses are refused; redirects are reported, not followed; each request stops after 4 seconds. Observations, not witnessed evidence, not a grade.

ParametersJSON Schema
NameRequiredDescriptionDefault
domainYesDomain to read, e.g. example.com

Output Schema

ParametersJSON Schema
NameRequiredDescription
statusYesMachine-branchable outcome for this lookup.
subjectYesThe company, domain or token this answer is about.
summaryYesThe same answer as the text content, for display.
evidenceNoPresent on a published profile. What this answer is built from, what it leaves out, and where to get the rest. The summary is a summary: the typed facts with their provenance are in the record at full_record.
claim_urlNoPresent when the subject has no published record (unclaimed or private).
provenanceYesWhere this answer came from. An honest_absence is missing data, never a judgment about the subject. A read_failed means Trooth could not read its own record at this moment and asserts nothing either way; retry rather than concluding. witnessed_reading: a published profile whose reading Trooth witnessed; the profile is not signed, and the one signed object is the reading's witness statement (see evidence.signed_artifact). connected_system_reads: read from systems the company connected. ledger_token_signatures: the result of checking a Trust Ledger Token's two signatures; the claims inside it stay the company's. witnessed_signed is DEPRECATED since 2026-09-26 and no longer returned; it meant any of the three above.

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare readOnly/openWorld/idempotent behavior, and the description adds substantial behavioral detail beyond them: requests originate from Trooth's server, run once, stop after 4 seconds, redirects are not followed, and private/loopback/link-local names are refused. It also clarifies epistemic status as observations.

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 dense but not bloated: each clause adds operational or interpretive information. The main action is front-loaded, followed by constraints and result framing, with no wasted words.

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

Completeness5/5

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

With an output schema present, the description need not restate return values. It covers edge cases (private addresses, redirects, timeouts) and result interpretation, making it fully sufficient for an agent to select and invoke the tool correctly.

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

Parameters4/5

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

The schema covers the single 'domain' parameter at 100%, so the baseline is 3. The description adds value by clarifying that IP literals and names resolving to private/loopback/link-local addresses are rejected, and that the domain is fetched from Trooth's server.

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

Purpose5/5

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

The description names a specific verb and resource: 'Fetch https://<domain>/ and /.well-known/security.txt once... and report'. It enumerates the exact outputs (HTTPS answered, five headers, security.txt status), making it distinguishable from sibling tools like trooth_verify.

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

Usage Guidelines4/5

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

It gives clear operational context: one-shot read from Trooth's server, with refusals, redirects, and timeout behavior. The phrase 'Observations, not witnessed evidence, not a grade' serves as an exclusion for evidence-grade use, though it does not explicitly name sibling alternatives.

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

trooth_public_trust_profileA
Read-onlyIdempotent
Inspect

Read one company's published record on the Trooth Network, given its domain or Trooth slug. The identifier is matched exactly (a URL is reduced to its host), never by a similar name. Returns a status (published, listed, private, unclaimed or unavailable) and a provenance label; text the company wrote about itself is labeled as its own words. Read only.

ParametersJSON Schema
NameRequiredDescriptionDefault
companyYesCompany domain (e.g. acme.com) or Trooth slug

Output Schema

ParametersJSON Schema
NameRequiredDescription
statusYesMachine-branchable outcome for this lookup.
subjectYesThe company, domain or token this answer is about.
summaryYesThe same answer as the text content, for display.
evidenceNoPresent on a published profile. What this answer is built from, what it leaves out, and where to get the rest. The summary is a summary: the typed facts with their provenance are in the record at full_record.
claim_urlNoPresent when the subject has no published record (unclaimed or private).
provenanceYesWhere this answer came from. An honest_absence is missing data, never a judgment about the subject. A read_failed means Trooth could not read its own record at this moment and asserts nothing either way; retry rather than concluding. witnessed_reading: a published profile whose reading Trooth witnessed; the profile is not signed, and the one signed object is the reading's witness statement (see evidence.signed_artifact). connected_system_reads: read from systems the company connected. ledger_token_signatures: the result of checking a Trust Ledger Token's two signatures; the claims inside it stay the company's. witnessed_signed is DEPRECATED since 2026-09-26 and no longer returned; it meant any of the three above.

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered. The description adds valuable behavioral details: matching is exact, URLs are reduced to host, never similar names, and the output includes a status list and provenance label. This goes beyond the annotations and helps the agent understand edge-case behavior (e.g., exact match only).

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 sentences, front-loaded with the primary purpose, followed by matching rules and output summary. Every sentence adds essential information without redundancy. No filler or unnecessary elaboration, making it efficient and well-structured.

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 single-parameter read-only tool with an output schema present, the description sufficiently covers input semantics, matching behavior, and the key output components (status and provenance). It lists all possible statuses and explains how self-authored text is labeled. Minor gaps like error handling or exact provenance format are not critical given the output schema exists and the operation is read-only.

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

Parameters4/5

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

The schema already describes the 'company' parameter as a domain or slug (100% coverage). The description adds critical nuance: it explains that the identifier is matched exactly, and a URL is reduced to its host. This clarifies how the parameter is interpreted, which is not evident from the schema alone. Thus it enriches the semantic meaning beyond the structural definition.

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

Purpose5/5

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

The description clearly states the specific action: 'Read one company's published record on the Trooth Network' with the input being a domain or slug. It goes beyond the title by specifying exact matching behavior, distinguishing it from sibling tools like trooth_ask or trooth_verify which likely serve different purposes. The verb, resource, and matching constraint are unambiguous.

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

Usage Guidelines4/5

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

The description gives clear context for use: when you need to read a company's public trust record, given its domain or slug. It does not explicitly mention when not to use it or name alternatives, but the read-only nature and specific resource are enough for an agent to infer the appropriate situation. No exclusions are provided, but the context is clear.

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

trooth_verifyA
Read-onlyIdempotent
Inspect

Check the two signatures on a Trust Ledger Token (tlt2. or tlt. form, or its JTI) against Trooth's own token ledger. Returns valid, invalid (a signature does not check out), expired or revoked, or unclaimed when no token matches. Trooth's signature covers the signing event, not the claim bytes and not the truth of the claims; the issuing company's signature covers the payload.

ParametersJSON Schema
NameRequiredDescriptionDefault
tokenYesA Trust Ledger Token (tlt2. or tlt. form) or its JTI

Output Schema

ParametersJSON Schema
NameRequiredDescription
statusYesMachine-branchable outcome for this lookup.
subjectYesThe company, domain or token this answer is about.
summaryYesThe same answer as the text content, for display.
evidenceNoPresent on a published profile. What this answer is built from, what it leaves out, and where to get the rest. The summary is a summary: the typed facts with their provenance are in the record at full_record.
claim_urlNoPresent when the subject has no published record (unclaimed or private).
provenanceYesWhere this answer came from. An honest_absence is missing data, never a judgment about the subject. A read_failed means Trooth could not read its own record at this moment and asserts nothing either way; retry rather than concluding. witnessed_reading: a published profile whose reading Trooth witnessed; the profile is not signed, and the one signed object is the reading's witness statement (see evidence.signed_artifact). connected_system_reads: read from systems the company connected. ledger_token_signatures: the result of checking a Trust Ledger Token's two signatures; the claims inside it stay the company's. witnessed_signed is DEPRECATED since 2026-09-26 and no longer returned; it meant any of the three above.

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds valuable context beyond that: the distinct signature scopes (Trooth's signature covers the signing event, not claim bytes or truth; the issuing company's signature covers the payload) and the full set of possible return states (valid, invalid, expired, revoked, unclaimed). This enriches the agent's mental model of the verification semantics.

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 two sentences with zero filler. The first sentence states the exact action and scope; the second provides the critical nuance about signature coverage. Every word earns its place, and the most important information is front-loaded.

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

Completeness5/5

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

The tool takes a single parameter with full schema coverage, has an output schema (not shown but indicated), and the description explains the return states and the semantics of the two signatures. Given the simplicity and existing annotations, nothing an agent needs to call it correctly is missing.

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% for the single 'token' parameter, so the schema already documents it as 'A Trust Ledger Token (tlt2. or tlt. form) or its JTI'. The description repeats the token forms but adds no new semantics beyond reinforcing what the schema states. At full coverage, baseline 3 is appropriate.

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

Purpose5/5

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

The description clearly states a specific verb ('Check') and resource ('two signatures on a Trust Ledger Token') and defines the scope (tlt2./tlt. forms or JTI). It distinguishes itself from sibling tools by focusing on signature verification, which is not implied by any sibling's name.

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

Usage Guidelines4/5

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

The description implicitly conveys when to use this tool—when you need to check a token's signatures—but does not explicitly name alternatives or state when not to use it. Given the sibling names (ask, outside_in_read, public_trust_profile), the context is clear enough for an agent to route correctly, though explicit exclusions would push it higher.

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
    • Changedtrooth_ask3 fields changed
      • addedOutput schema / properties / evidence
        Added value: +{
+  "description": "Present on a published profile. What this answer is built from, what it leaves out, and where to get the rest. The summary is a summary: the typed facts with their provenance are in the record at full_record.",
+  "properties": {
+    "counts": {
+      "description": "The reading's counts, from the source named. witness_statement: read, as expected and not read in this reading. result_tally: an older reading's own tally, not a count of checks read.",
+      "properties": {
+        "as_expected": {
+          "type": "integer"
+        },
+        "in_reading": {
+          "type": [
+            "integer",
+            "null"
+          ]
+        },
+        "not_read": {
+          "type": [
+            "integer",
+            "null"
+          ]
+        },
+        "read": {
+          "type": "integer"
+        },
+        "source": {
+          "enum": [
+            "witness_statement",
+            "result_tally"
+          ],
+          "type": "string"
+        }
+      },
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "facts_published": {
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "full_record": {
+      "description": "The canonical record as JSON, contract 2, with every typed fact, its provenance and its date where known.",
+      "type": "string"
+    },
+    "last_witnessed": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "omitted": {
+      "description": "What the summary leaves out. Every item is in full_record.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "profile_signed": {
+      "description": "Always false. The profile is not signed.",
+      "type": "boolean"
+    },
+    "schema": {
+      "type": "string"
+    },
+    "signed_artifact": {
+      "description": "The one signed object behind this answer, or null when the reading carries none. It is served, byte for byte as signed, in the witnessStatement field of full_record.",
+      "properties": {
+        "covers": {
+          "type": "string"
+        },
+        "key_id": {
+          "type": "string"
+        },
+        "read_at": {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "type": {
+          "type": "string"
+        },
+        "verify": {
+          "type": "string"
+        }
+      },
+      "type": [
+        "object",
+        "null"
+      ]
+    }
+  },
+  "type": "object"
+}
      • changedOutput schema / properties / provenance / description
        Previous value: -"Where this answer came from. An honest_absence is missing data, never a judgment about the subject. A read_failed means Trooth could not read its own record at this moment and asserts nothing either way; retry rather than concluding."New value: +"Where this answer came from. An honest_absence is missing data, never a judgment about the subject. A read_failed means Trooth could not read its own record at this moment and asserts nothing either way; retry rather than concluding. witnessed_reading: a published profile whose reading Trooth witnessed; the profile is not signed, and the one signed object is the reading's witness statement (see evidence.signed_artifact). connected_system_reads: read from systems the company connected. ledger_token_signatures: the result of checking a Trust Ledger Token's two signatures; the claims inside it stay the company's. witnessed_signed is DEPRECATED since 2026-09-26 and no longer returned; it meant any of the three above."
      • changedOutput schema / properties / provenance / enum
        Previous value: -[
-  "witnessed_signed",
-  "signed_scan",
-  "live_observation",
-  "honest_absence",
-  "withheld_by_owner",
-  "knowledge_base",
-  "input_error",
-  "self_declared",
-  "read_failed"
-]New value: +[
+  "witnessed_reading",
+  "connected_system_reads",
+  "ledger_token_signatures",
+  "witnessed_signed",
+  "signed_scan",
+  "live_observation",
+  "honest_absence",
+  "withheld_by_owner",
+  "knowledge_base",
+  "input_error",
+  "self_declared",
+  "read_failed"
+]
    • Changedtrooth_outside_in_read3 fields changed
      • addedOutput schema / properties / evidence
        Added value: +{
+  "description": "Present on a published profile. What this answer is built from, what it leaves out, and where to get the rest. The summary is a summary: the typed facts with their provenance are in the record at full_record.",
+  "properties": {
+    "counts": {
+      "description": "The reading's counts, from the source named. witness_statement: read, as expected and not read in this reading. result_tally: an older reading's own tally, not a count of checks read.",
+      "properties": {
+        "as_expected": {
+          "type": "integer"
+        },
+        "in_reading": {
+          "type": [
+            "integer",
+            "null"
+          ]
+        },
+        "not_read": {
+          "type": [
+            "integer",
+            "null"
+          ]
+        },
+        "read": {
+          "type": "integer"
+        },
+        "source": {
+          "enum": [
+            "witness_statement",
+            "result_tally"
+          ],
+          "type": "string"
+        }
+      },
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "facts_published": {
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "full_record": {
+      "description": "The canonical record as JSON, contract 2, with every typed fact, its provenance and its date where known.",
+      "type": "string"
+    },
+    "last_witnessed": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "omitted": {
+      "description": "What the summary leaves out. Every item is in full_record.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "profile_signed": {
+      "description": "Always false. The profile is not signed.",
+      "type": "boolean"
+    },
+    "schema": {
+      "type": "string"
+    },
+    "signed_artifact": {
+      "description": "The one signed object behind this answer, or null when the reading carries none. It is served, byte for byte as signed, in the witnessStatement field of full_record.",
+      "properties": {
+        "covers": {
+          "type": "string"
+        },
+        "key_id": {
+          "type": "string"
+        },
+        "read_at": {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "type": {
+          "type": "string"
+        },
+        "verify": {
+          "type": "string"
+        }
+      },
+      "type": [
+        "object",
+        "null"
+      ]
+    }
+  },
+  "type": "object"
+}
      • changedOutput schema / properties / provenance / description
        Previous value: -"Where this answer came from. An honest_absence is missing data, never a judgment about the subject. A read_failed means Trooth could not read its own record at this moment and asserts nothing either way; retry rather than concluding."New value: +"Where this answer came from. An honest_absence is missing data, never a judgment about the subject. A read_failed means Trooth could not read its own record at this moment and asserts nothing either way; retry rather than concluding. witnessed_reading: a published profile whose reading Trooth witnessed; the profile is not signed, and the one signed object is the reading's witness statement (see evidence.signed_artifact). connected_system_reads: read from systems the company connected. ledger_token_signatures: the result of checking a Trust Ledger Token's two signatures; the claims inside it stay the company's. witnessed_signed is DEPRECATED since 2026-09-26 and no longer returned; it meant any of the three above."
      • changedOutput schema / properties / provenance / enum
        Previous value: -[
-  "witnessed_signed",
-  "signed_scan",
-  "live_observation",
-  "honest_absence",
-  "withheld_by_owner",
-  "knowledge_base",
-  "input_error",
-  "self_declared",
-  "read_failed"
-]New value: +[
+  "witnessed_reading",
+  "connected_system_reads",
+  "ledger_token_signatures",
+  "witnessed_signed",
+  "signed_scan",
+  "live_observation",
+  "honest_absence",
+  "withheld_by_owner",
+  "knowledge_base",
+  "input_error",
+  "self_declared",
+  "read_failed"
+]
    • Changedtrooth_public_trust_profile3 fields changed
      • addedOutput schema / properties / evidence
        Added value: +{
+  "description": "Present on a published profile. What this answer is built from, what it leaves out, and where to get the rest. The summary is a summary: the typed facts with their provenance are in the record at full_record.",
+  "properties": {
+    "counts": {
+      "description": "The reading's counts, from the source named. witness_statement: read, as expected and not read in this reading. result_tally: an older reading's own tally, not a count of checks read.",
+      "properties": {
+        "as_expected": {
+          "type": "integer"
+        },
+        "in_reading": {
+          "type": [
+            "integer",
+            "null"
+          ]
+        },
+        "not_read": {
+          "type": [
+            "integer",
+            "null"
+          ]
+        },
+        "read": {
+          "type": "integer"
+        },
+        "source": {
+          "enum": [
+            "witness_statement",
+            "result_tally"
+          ],
+          "type": "string"
+        }
+      },
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "facts_published": {
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "full_record": {
+      "description": "The canonical record as JSON, contract 2, with every typed fact, its provenance and its date where known.",
+      "type": "string"
+    },
+    "last_witnessed": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "omitted": {
+      "description": "What the summary leaves out. Every item is in full_record.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "profile_signed": {
+      "description": "Always false. The profile is not signed.",
+      "type": "boolean"
+    },
+    "schema": {
+      "type": "string"
+    },
+    "signed_artifact": {
+      "description": "The one signed object behind this answer, or null when the reading carries none. It is served, byte for byte as signed, in the witnessStatement field of full_record.",
+      "properties": {
+        "covers": {
+          "type": "string"
+        },
+        "key_id": {
+          "type": "string"
+        },
+        "read_at": {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "type": {
+          "type": "string"
+        },
+        "verify": {
+          "type": "string"
+        }
+      },
+      "type": [
+        "object",
+        "null"
+      ]
+    }
+  },
+  "type": "object"
+}
      • changedOutput schema / properties / provenance / description
        Previous value: -"Where this answer came from. An honest_absence is missing data, never a judgment about the subject. A read_failed means Trooth could not read its own record at this moment and asserts nothing either way; retry rather than concluding."New value: +"Where this answer came from. An honest_absence is missing data, never a judgment about the subject. A read_failed means Trooth could not read its own record at this moment and asserts nothing either way; retry rather than concluding. witnessed_reading: a published profile whose reading Trooth witnessed; the profile is not signed, and the one signed object is the reading's witness statement (see evidence.signed_artifact). connected_system_reads: read from systems the company connected. ledger_token_signatures: the result of checking a Trust Ledger Token's two signatures; the claims inside it stay the company's. witnessed_signed is DEPRECATED since 2026-09-26 and no longer returned; it meant any of the three above."
      • changedOutput schema / properties / provenance / enum
        Previous value: -[
-  "witnessed_signed",
-  "signed_scan",
-  "live_observation",
-  "honest_absence",
-  "withheld_by_owner",
-  "knowledge_base",
-  "input_error",
-  "self_declared",
-  "read_failed"
-]New value: +[
+  "witnessed_reading",
+  "connected_system_reads",
+  "ledger_token_signatures",
+  "witnessed_signed",
+  "signed_scan",
+  "live_observation",
+  "honest_absence",
+  "withheld_by_owner",
+  "knowledge_base",
+  "input_error",
+  "self_declared",
+  "read_failed"
+]
    • Changedtrooth_verify3 fields changed
      • addedOutput schema / properties / evidence
        Added value: +{
+  "description": "Present on a published profile. What this answer is built from, what it leaves out, and where to get the rest. The summary is a summary: the typed facts with their provenance are in the record at full_record.",
+  "properties": {
+    "counts": {
+      "description": "The reading's counts, from the source named. witness_statement: read, as expected and not read in this reading. result_tally: an older reading's own tally, not a count of checks read.",
+      "properties": {
+        "as_expected": {
+          "type": "integer"
+        },
+        "in_reading": {
+          "type": [
+            "integer",
+            "null"
+          ]
+        },
+        "not_read": {
+          "type": [
+            "integer",
+            "null"
+          ]
+        },
+        "read": {
+          "type": "integer"
+        },
+        "source": {
+          "enum": [
+            "witness_statement",
+            "result_tally"
+          ],
+          "type": "string"
+        }
+      },
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "facts_published": {
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "full_record": {
+      "description": "The canonical record as JSON, contract 2, with every typed fact, its provenance and its date where known.",
+      "type": "string"
+    },
+    "last_witnessed": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "omitted": {
+      "description": "What the summary leaves out. Every item is in full_record.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "profile_signed": {
+      "description": "Always false. The profile is not signed.",
+      "type": "boolean"
+    },
+    "schema": {
+      "type": "string"
+    },
+    "signed_artifact": {
+      "description": "The one signed object behind this answer, or null when the reading carries none. It is served, byte for byte as signed, in the witnessStatement field of full_record.",
+      "properties": {
+        "covers": {
+          "type": "string"
+        },
+        "key_id": {
+          "type": "string"
+        },
+        "read_at": {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "type": {
+          "type": "string"
+        },
+        "verify": {
+          "type": "string"
+        }
+      },
+      "type": [
+        "object",
+        "null"
+      ]
+    }
+  },
+  "type": "object"
+}
      • changedOutput schema / properties / provenance / description
        Previous value: -"Where this answer came from. An honest_absence is missing data, never a judgment about the subject. A read_failed means Trooth could not read its own record at this moment and asserts nothing either way; retry rather than concluding."New value: +"Where this answer came from. An honest_absence is missing data, never a judgment about the subject. A read_failed means Trooth could not read its own record at this moment and asserts nothing either way; retry rather than concluding. witnessed_reading: a published profile whose reading Trooth witnessed; the profile is not signed, and the one signed object is the reading's witness statement (see evidence.signed_artifact). connected_system_reads: read from systems the company connected. ledger_token_signatures: the result of checking a Trust Ledger Token's two signatures; the claims inside it stay the company's. witnessed_signed is DEPRECATED since 2026-09-26 and no longer returned; it meant any of the three above."
      • changedOutput schema / properties / provenance / enum
        Previous value: -[
-  "witnessed_signed",
-  "signed_scan",
-  "live_observation",
-  "honest_absence",
-  "withheld_by_owner",
-  "knowledge_base",
-  "input_error",
-  "self_declared",
-  "read_failed"
-]New value: +[
+  "witnessed_reading",
+  "connected_system_reads",
+  "ledger_token_signatures",
+  "witnessed_signed",
+  "signed_scan",
+  "live_observation",
+  "honest_absence",
+  "withheld_by_owner",
+  "knowledge_base",
+  "input_error",
+  "self_declared",
+  "read_failed"
+]
  2. 4 tool updates
    • First observedtrooth_ask
    • First observedtrooth_outside_in_read
    • First observedtrooth_public_trust_profile
    • First observedtrooth_verify

Related MCP Connectors

Related MCP Servers

Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources