Skip to main content
Glama
probityai-archive

agent-evidence-mcp

Official

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
verify_claimC

Decide one claim against evidence bytes the caller supplies, with probity-verify.

verify_sampleC

Run a bundled sample claim: contradicted, not_established or supported.

list_vector_corporaA

Name every shipped corpus with its suite revision and vector counts where it declares them.

run_vectorsB

Replay one corpus with the bundled reference verifier; per-vector rows come back in pages.

explain_vectorC

Return one vector: its manifest entry, the conditions it tests, and its input bytes.

lookup_termA

Look a term up in the released vocabulary by exact key; otherwise suggest close keys.

check_artifact_digestB

Check that an artifact has a digest a TEA, CycloneDX or in-toto document names.

canonicalize_jsonC

Admit one JSON document and return its RFC 8785 canonical bytes, with the jcs-admit crate.

verify_dsseC

Verify a DSSE envelope against Ed25519 keys the caller trusts, with the dsse crate.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3.4/5.0

Scored across 9 tools

Disambiguation4/5

Most tools have clearly distinct roles: digest checking, JSON canonicalization, DSSE verification, claim verification, vector corpus operations, and term lookup. The only mild overlap is between verify_claim, verify_sample, and run_vectors, since all involve running verification logic, but their descriptions distinguish live claims, bundled samples, and corpus replay.

Naming Consistency5/5

All tool names use consistent snake_case with a verb_noun or verb_object pattern: check_artifact_digest, canonicalize_json, verify_dsse, verify_claim, verify_sample, list_vector_corpora, run_vectors, explain_vector, lookup_term. There are no mixed conventions or vague standalone names.

Tool Count5/5

Nine tools is a well-scoped set for a focused evidence-verification server. Each tool maps to a distinct operation across canonicalization, verification, vector replay, and vocabulary lookup without excessive surface area.

Completeness4/5

The server covers core verification workflows: digest checking, JSON canonicalization, DSSE and claim verification, sample checks, vector corpus inspection/replay, and vocabulary lookup. Minor gaps may exist around artifact fetching/parsing or signing/generation, but the verification lifecycle is largely covered.

Maintenance

ActivityMaintained
ResponsivenessNo issues