attest — verification for AI agent artifacts is an MCP server published by io.github.mrpkk, hosted at attest.rta.lat. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 2 tools, including verify_artifact, verify_artifact_batch.
Verify an AI agent artifact: schema, emptiness, provenance and mandate authority, Ed25519-signed.
20 connections through 5 shared values. Tap any node.
Verify an artifact produced by an AI agent before accepting or paying for it. Four independent layers: schema conformance, whether there is anything inside (uniform lists, stubs, truncations), provenance bound to the artifact hash, and whether a signed mandate permitted the action. Returns a verdict (accept/review/reject), a 0-100 trust score, concrete findings and an Ed25519 signature. Rule-based, no LLM: the same artifact always yields the same result. Use before accepting work from another agent and before payment.
| Parameter | Type | Description |
|---|---|---|
| schema | object | Optional JSON Schema the artifact must satisfy. |
| source | string | Where the artifact came from, recorded in the attestation. |
| artifact * | any | The agent artifact: object, array or string. |
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
{
"name": "verify_artifact",
"title": "Verify an AI agent artifact",
"description": "Verify an artifact produced by an AI agent before accepting or paying for it. Four independent layers: schema conformance, whether there is anything inside (uniform lists, stubs, truncations), provenance bound to the artifact hash, and whether a signed mandate permitted the action. Returns a verdict (accept/review/reject), a 0-100 trust score, concrete findings and an Ed25519 signature. Rule-based, no LLM: the same artifact always yields the same result. Use before accepting work from another agent and before payment.",
"inputSchema": {
"type": "object",
"required": [
"artifact"
],
"properties": {
"schema": {
"type": "object",
"description": "Optional JSON Schema the artifact must satisfy."
},
"source": {
"type": "string",
"description": "Where the artifact came from, recorded in the attestation."
},
"artifact": {
"description": "The agent artifact: object, array or string."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Verify an AI agent artifact",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Verify several artifacts at once — a scan report, a list of findings, a set of tool descriptions. One call, one verdict per artifact, plus a summary of how many were accepted, need review, or were rejected. Use when an agent produced a batch (twenty findings from a security scan, for example) and each of them has to be checked before the work is paid for.
| Parameter | Type | Description |
|---|---|---|
| schema | object | Optional JSON Schema every artifact must satisfy. |
| source | string | Where the artifacts came from, recorded in the attestations. |
| artifacts * | array | The artifacts to verify: objects, arrays or strings. |
{
"name": "verify_artifact_batch",
"title": "Verify a batch of AI agent artifacts",
"description": "Verify several artifacts at once — a scan report, a list of findings, a set of tool descriptions. One call, one verdict per artifact, plus a summary of how many were accepted, need review, or were rejected. Use when an agent produced a batch (twenty findings from a security scan, for example) and each of them has to be checked before the work is paid for.",
"inputSchema": {
"type": "object",
"required": [
"artifacts"
],
"properties": {
"schema": {
"type": "object",
"description": "Optional JSON Schema every artifact must satisfy."
},
"source": {
"type": "string",
"description": "Where the artifacts came from, recorded in the attestations."
},
"artifacts": {
"type": "array",
"description": "The artifacts to verify: objects, arrays or strings."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Verify a batch of AI agent artifacts",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.