verify-mcp
Verifies npm packages (by name and version) by querying OSV.dev advisories, returning an evidence report with pass/fail/unknown verdicts rather than a simple checkmark.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
verify-mcp
A sketch of a "trust layer" MCP server: one verify tool an agent calls
before acting on data it did not produce. It returns an evidence report,
not a checkmark.
Companion to the talk Invisible Data: Building Trust in the Age of AI.
Run
npm install
npm run build
claude mcp add verify -- node /path/to/verify-mcp/dist/cli.jsRelated MCP server: Recommend Agentic Trust Layer
The tool
verify({ target })target is one of:
kind | example input | checks |
|
| OSV.dev advisories |
|
| JSON Schema contract (incl. |
|
| C2PA manifest (c2patool) |
|
| independent-source corroboration (heuristic) |
Units: x-unit
A property with "x-unit": "N*s" must be sent as { "value": 4.45, "unit": "N*s" }.
A different unit (lbf*s) or a bare number is a high finding. Only separators are
normalised (N·s = N*s = N s); there are no aliases and no conversion.
Schemas are compiled in Ajv strict mode: an unknown or misspelled keyword makes the
check error instead of silently passing. x-* keys are allowed as annotations.
C2PA: c2patool
Install c2patool (tested with 0.27.23, verify the release checksum) and point the server at it:
claude mcp add verify \
-e VERIFY_MCP_C2PATOOL=/path/to/c2patool \
-e C2PATOOL_TRUST_ANCHORS=/path/to/anchors.pem \
-- node /path/to/verify-mcp/dist/cli.jsC2PATOOL_TRUST_ANCHORS, C2PATOOL_TRUST_CONFIG and C2PATOOL_ALLOWED_LIST are
c2patool's own settings. Only a Trusted manifest passes; Invalid fails; a
manifest from an untrusted signer, or no manifest at all, is skipped, so the
verdict stays unknown.
The report
{
"verdict": "pass" | "fail" | "unknown",
"summary": "Failed: 1/2 checks completed, 2 finding(s).",
"checks": [{ "id", "kind", "status", "source": { "name", "retrievedAt" }, "findings", "reason" }],
"notChecked": ["Whether values are true, only whether they are well-formed", "…"],
"generatedAt": "…",
"verifier": { "name": "verify-mcp", "version": "0.1.0" }
}Rules baked in
Evidence, not verdicts. Every check lists its source and timestamp.
notCheckedis always present, so limits are never silent.Deterministic first. Checks are labelled
deterministicorheuristic. Heuristics can fail a target but can never pass it alone.Independent checks. No LLM "plausibility" scoring. The verifier never asks the generator to grade itself.
Unknown ≠ verified. A required check that errors or is skipped makes the verdict
unknown. Exceptions becomeerror, never a crash or a pass.Verify the verifier. This server is a dependency too: pin it, scan it, and keep it read-only (
readOnlyHint: true).
What's stubbed
checkObservability: wire to Monte Carlo, Soda, Elementary, etc. (their API, or act as an MCP client to their MCP server).checkCorroboration: fetches nothing yet; only enforces two distinct source domains.
Ideas for v0.2
verifyover a lockfile or SBOM (OSV batch API).A signed report (Sigstore) so downstream systems can trust the verifier's output, not just the agent's summary of it.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
One-stop claim verification for AI agents: verdicts with confidence, evidence, signed receipts.
Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST.
Bounded authorization and independently verifiable execution evidence for agents.
Verifiable execution records for AI agents: signed receipts, tamper-evident archives and portable evidence bundles, exposed via MCP and REST, with paid verify and anchor calls settled over x402.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to query cryptographically verified facts with zero-knowledge proofs, selective disclosure, and tamper-evident provenance.1Business Source 1.1
- AlicenseNot gradedqualityCmaintenanceEnables agents to verify claims with evidence-based truth scores and confidence levels by running a deterministic pipeline of evidence lanes and adversarial checks.26MIT
- AlicenseAqualityCmaintenanceEnables production-grade answer verification for LLM agents by independently re-checking answers with a configurable verifier model, enforcing confidence policies, and producing Ed25519-signed, auditable verification results with optional web search and knowledge-base evidence.3MIT
- AlicenseNot gradedqualityBmaintenanceEnables deterministic verification of AI agent decisions and actions, providing PASS/FAIL/ABSTAIN verdicts with replayable proofs and an optional signed receipt ledger.4 npmApache 2.0