Aziel Runtime

Step 3 — Call the picked slug through FragGate

fraggate_call

Execute the slug you picked from Softwares through the FragGate single door (CallEnvelope → FragGate → Lamb Lens → SweepGate → Sentinel → Provenance → ChainLock-IN → DecisionGATE → AZPIPE → Internal Domain Layer → optional ASE → RoseClock → TemporalLock → ChainLock-OUT → ForgeReceipts → Return). Default exec path — not the catalog and not a raw session. Use this when Softwares already returned a slug and a live allowlisted op is known. Do not use it for picking the catalog slug, searching library papers, or raw session plumbing; use Softwares, library_lookup, or (only if asked) runtime_run / runtime_session_exec instead. Side effects are operation-dependent (read, write, or refuse). May reach an open world when the target op does (for example AZBrowser ethical_search); many ops stay isolate-local. Unknown names refuse FG-HALLUC-TOOL. Stub, local-only, and Remain-OFF verbs refuse FG-STUB / FG-LOCAL-ONLY / FG-GATE-REFUSE / FG-LAMB-REFUSE. FragGate is THE single door. Required: op, unless job_id is set (that reads a background job and does not start another). Also pass slug or name. Shorthand name foldlock/fold-preview is accepted. Extra top-level keys other than name/slug/product/tool/op/verb/claim/proposal/ground/payload/session_id/id/confirm/dry_run/background/job_id become the op payload when payload is omitted. Example preview: {"name":"foldlock/fold-preview","payload":{"text":"the cat and the dog"},"dry_run":true}. Optional background=true returns Running and a job_id before the op finishes; Done only after a receipt hash exists. Poll with the same job_id and confirm=true. dry_run does not start a job. UI aliases (list_modules, place, genesis_boot, hold, airlock, home, classify, doctor, pair) forward to catalog ops. Mutation requires confirm=true (runtime gate) or dry_run=true (preview only, no write). confirm and dry_run stay optional on inputSchema.required. dry_run still returns FG-HALLUC-TOOL, FG-STUB, FG-UNKNOWN-OP, or FG-LOCAL-ONLY when a confirm call would refuse. confirm is consent, not tenant auth, and it does not upgrade shared public-demo isolation. Returns status, result, receipt, engine_slug, engine_op, engine_digest, ran_in, provenance, refusal, and limitations. Not the full FragGate door. Empty fraggate_list is discovery (hashed LIVE_OPS). Catalog LIVE_OPS slugs (40): 4dmap, ark, azai, azbot, azbrowser, azchat, azclce, azcoherence, azhub, aziel-corpus, azieltether, azinterface, azmail, aznet, azos, azvpn, chronolock, codelock, decisiongate, embryolock, employeelock, foldlock, forgereceipts, glossafilter, godlock, mialock, miragegrid, mmconsensus, peacelock, postking, shadowlock, spectrallock, staticclock, temporallock, toolbench, trajectorylock, vibelock, whistlelock, zkattest, zsolver. Compact product-verify tokens (not a second allowlist): allowlist.azhub LIVE_OPS: health, skill, region_list, place_module, remove_module, tether_declare, tether_cut, tether_list, blank_key_status, list_modules, place. allowlist.azinterface LIVE_OPS: health, skill, genesis_status, site_state_get, site_state_set, integrity_check, witness_list, page_cycle_status, mesh_radios, genesis_boot, hold. allowlist.azbrowser LIVE_OPS: ethical_search, lamb_lens_search, navigate, airlock_ingest, airlock, home, tab_open, tab_list, receipt_list, verify, receipt_verify, sandbox_status, sandbox_render, health, skill, vpn. allowlist.azvpn LIVE_OPS: health, skill, doctor, limitation, describe, open, status, list, close, send, recv, pull, peers, attach. allowlist.aznet LIVE_OPS: health, doctor, pair_status, pair, garden_list, stamp, verify_hash, memorial_list, memorial_append, receipt_verify, name_claim, name_read, name_resolve, slot_read, witness, witness_read, skill. UI aliases forward to catalog ops. EmbryoLock LIVE_OPS health/skill/doctor/verify-hash/policy/limitation; wipe/scorch/unlock stay FG-STUB on the public mesh.

Input Schema

TableJSON Schema

Name	Required	Description
`op`	Yes	Required public allowlisted op from fraggate_describe (for example fold-preview, ethical_search, blank_key_status). UI aliases (list_modules, place, genesis_boot, hold, airlock, home, classify, doctor, pair) forward to catalog ops. Unknown ops refuse FG-UNKNOWN-OP; stubs refuse FG-STUB.
`name`	No	Optional registry display name (for example FoldLock, EmbryoLock, AZHub). Use name or slug — one is enough. Combined name/op forms such as foldlock/fold-preview are accepted by the door parser. Unknown names refuse FG-HALLUC-TOOL.
`slug`	No	Optional catalog slug (lowercase a-z0-9-, for example foldlock, embryolock, azhub). Alternative to name. Prefer the slug returned by fraggate_list or GET /v1/software.
`claim`	No	Optional DecisionGATE proposal attached to this call. Also runs automatically inside the door even when omitted (defaults). Freedom without clarity is chaos.
`job_id`	No	Optional job id from a background call (job_ + 16 hex). When set, the call reads that job and does not start another. confirm=true is still required. It does not re-run the op.
`confirm`	No	Documented confirmation flag. Optional in inputSchema.required (connector refresh must not break). tools/call still refuses MCP-CONFIRM-REQUIRED when confirm is missing or false unless dry_run=true. confirm is consent to run the call. It is not tenant auth and it does not upgrade shared public-demo isolation.
`dry_run`	No	Optional preview flag. When true, do not write and do not stamp a ledger tip. Allowlist, hallucination, stub, and local-only checks still run and return the same FragGate refuse code a confirm call would get. MCP-DRY-RUN is returned only when that call would have been allowed to proceed. confirm is consent, not tenant auth, and it does not upgrade shared public-demo isolation.
`payload`	No	Optional op payload object. Shape is engine-specific (see fraggate_describe). Malformed fields are refused by the engine, not by this door schema. If omitted, leftover top-level keys are used as the payload.
`attempt_n`	No	Optional 1-based attempt number for this call. Omitted means attempt 1 of a new request_id.
`background`	No	Optional. When true, FragGate admits the call and returns Running with a job_id before the op finishes. Done is returned only after a receipt hash exists. dry_run does not start a job. A missing job is Quiet, not Done.
`request_id`	No	Optional logical request id. The same value groups retries of one action on the ResultEnvelope and, for ForgeReceipts, inside the receipt hash.
`correlation_id`	No	Optional client correlation id. Sealed inside a ForgeReceipts hash when this call mints one.
`parent_receipt_id`	No	Optional prior attempt receipt hash. Null on the first attempt. This is not FragGate ledger prev, which stays call order only.

Output Schema

TableJSON Schema

Name	Required	Description
`code`	No	FragGate or fabric code when present: FG-OK, FG-HALLUC-TOOL, FG-STUB, FG-LOCAL-ONLY, FG-UNKNOWN-OP, FG-GATE-REFUSE, FG-LAMB-REFUSE, or a module refuse such as MESH-* / AKM-*.
`door`	No	Door name. The public door is fraggate.
`ran_in`	No	Execution locale (for example aziel-runtime) when present.
`result`	No	FragGate body: ok, code, door, slug, op, engine_digest, ran_in, provenance, refusal, limitations, receipt, plus the engine result. Unknown names refuse FG-HALLUC-TOOL; stubs refuse FG-STUB.
`status`	No	HTTP-like status when present on wrappers (200 ok; 400+ error / refuse).
`display`	No	Human-facing envelope. Show display.action, title, and summary, then take the next input. Never echo raw tool names.
`receipt`	No	Optional receipt, ledger tip, or TemporalLock/ForgeReceipts exit when the door stamped one.
`refusal`	No	Explicit refuse object, code, or message when the door or engine refused.
`engine_op`	No	Resolved engine op when present (often inside result).
`ledger_tip`	No	Ask/refuse ledger tip when the door stamped one.
`provenance`	No	Provenance / input packet when the pipeline attached one.
`session_id`	No	Raw session id when session plumbing was used. Hidden unless the user asked for the chain.
`engine_slug`	No	Resolved engine slug when present (often inside result).
`limitations`	No	Capability limitations or Remain-OFF notes when present.
`engine_digest`	No	64-hex engine_digest when a true in-process engine ran (often inside result).

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedSep 27, 2026

changedOutput schema / description

Previous value: -"Display envelope shown to the user (display.title / display.summary) plus the machine result. Extra engine fields may appear."New value: +"Display envelope shown to the user (display.action / display.title / display.summary) plus the machine result. Extra engine fields may appear. Do not echo raw tool names."

changedOutput schema / properties / display / description

Previous value: -"Human-facing envelope. Show title and summary, then take the next input."New value: +"Human-facing envelope. Show display.action, title, and summary, then take the next input. Never echo raw tool names."

addedOutput schema / properties / display / properties / action

Added value: +{
+  "description": "Human-visible run frame. Always \"Run aziel runtime\". Product verb titles stay on title. Not a tool name.",
+  "type": "string"
+}

addedOutput schema / properties / display / properties / image

Added value: +{
+  "additionalProperties": true,
+  "description": "Present only when a real production included png_b64, jpeg_b64 (or the same byte family), or a cited http(s) image URL. No invented thumbs. Omitted on dry_run. reviewed is true only when executed production bytes are attached; a dry_run never mints reviewed.",
+  "properties": {
+    "data": {
+      "description": "Base64 image bytes copied from the production. Omitted for a URL-only cite. Never present on dry_run.",
+      "type": "string"
+    },
+    "mimeType": {
+      "description": "Sniffed image media type (image/png, image/jpeg, image/webp, or image/gif).",
+      "type": "string"
+    },
+    "reviewed": {
+      "description": "True only when data came from an executed production. False for a URL cite without bytes. Never true on dry_run.",
+      "type": "boolean"
+    },
+    "source": {
+      "description": "Production field the image was taken from (for example png_b64, jpeg_b64, or image_url).",
+      "type": "string"
+    },
+    "url": {
+      "description": "Cited http(s) image URL when the production named one. Not invented.",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

changedOutput schema / properties / display / properties / title / description

Previous value: -"Short result title for the AI client."New value: +"Product verb title for the AI client. Not a raw tool name."

Changed3 schema fields changedSep 25, 2026

changedInput schema / description

Previous value: -"Required: op. Also pass slug or name. Extra top-level keys other than name/slug/product/tool/op/verb/claim/proposal/ground/payload/session_id/id become the op payload when payload is omitted. Mutation requires confirm=true or dry_run=true."New value: +"Required: op, unless job_id is set. Also pass slug or name. Shorthand foldlock/fold-preview is accepted. Mutation requires confirm=true or dry_run=true. background=true returns Running until a receipt hash exists."

addedInput schema / properties / background

Added value: +{
+  "description": "Optional. When true, FragGate admits the call and returns Running with a job_id before the op finishes. Done is returned only after a receipt hash exists. dry_run does not start a job. A missing job is Quiet, not Done.",
+  "type": "boolean"
+}

addedInput schema / properties / job_id

Added value: +{
+  "description": "Optional job id from a background call (job_ + 16 hex). When set, the call reads that job and does not start another. confirm=true is still required. It does not re-run the op.",
+  "pattern": "^job_[a-f0-9]{16}$",
+  "type": "string"
+}

Changed2 schema fields changedSep 25, 2026

changedInput schema / properties / confirm / description

Previous value: -"Documented confirmation flag. Optional in inputSchema.required (connector refresh must not break). tools/call still refuses MCP-CONFIRM-REQUIRED when confirm is missing or false unless dry_run=true (preview, no write)."New value: +"Documented confirmation flag. Optional in inputSchema.required (connector refresh must not break). tools/call still refuses MCP-CONFIRM-REQUIRED when confirm is missing or false unless dry_run=true. confirm is consent to run the call. It is not tenant auth and it does not upgrade shared public-demo isolation."

changedInput schema / properties / dry_run / description

Previous value: -"Optional preview flag. When true, return a would-mutate preview and do not write. Alternative to confirm=true. Does not mutate."New value: +"Optional preview flag. When true, do not write and do not stamp a ledger tip. Allowlist, hallucination, stub, and local-only checks still run and return the same FragGate refuse code a confirm call would get. MCP-DRY-RUN is returned only when that call would have been allowed to proceed. confirm is consent, not tenant auth, and it does not upgrade shared public-demo isolation."

First observedSep 24, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only cover the coarse safety profile (not read-only, open-world, non-idempotent, non-destructive); the description adds substantial behavior beyond that: operation-dependent side effects, specific refusal codes (FG-HALLUC-TOOL, FG-STUB, FG-LOCAL-ONLY), that dry_run still runs allowlist/hallucination/stub checks, and that confirm is consent not tenant auth. This is meaningful disclosure the annotations cannot express.

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

Conciseness2/5

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

Purpose and usage are front-loaded, which is good, but the body is heavily bloated with enumerations of all 40 catalog slugs, per-product allowlist op lists, and repetition of confirm/dry_run caveats. Much of this belongs in fraggate_list/fraggate_describe rather than the call tool's own description.

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?

For a complex 13-parameter mutating tool with a nested claim object and an output schema, the description covers required-vs-alternative params, refusal codes, async behavior, and mutation gating adequately. Return fields are listed but the output schema exists, so that is not a gap.

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%, so the baseline is 3, but the description adds real semantics beyond the schema: leftover top-level keys become the payload when payload is omitted, shorthand foldlock/fold-preview name/op folding, job_id polling with confirm=true, and background job lifecycle. Its main defect is hedging ('Not the full FragGate door') rather than parameter meaning.

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?

States a specific verb and resource ('Execute the slug you picked from Softwares through the FragGate single door') and immediately scopes it as the default exec path, explicitly not the catalog and not a raw session. An agent can differentiate it from fraggate_list, fraggate_describe, and runtime_session_exec without opening a schema.

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?

Gives an explicit when-to-use condition ('when Softwares already returned a slug and a live allowlisted op is known') plus explicit when-not ('Do not use it for picking the catalog slug, searching library papers, or raw session plumbing') with named alternatives (Softwares, library_lookup, runtime_run/runtime_session_exec). This is textbook routing guidance.

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

All Aziel Runtime tools Inspect

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.