← Index

AgentTrust

io.github.raditotev/agent-trust·v0.1.5·Other

MCP Server for Agent Reputation & Trust Scoring

Trust verdict · v1 advisory · method
NOT YET SCREENEDno verdict on file

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.

Own this server? Screen its description →

Environment variables
DATABASE_URL
required

PostgreSQL asyncpg connection string

REDIS_URL
required

Redis connection string

SIGNING_KEY_PATH
required

Path to Ed25519 private key PEM file

AUTH_PROVIDER

Authentication provider: agentauth | standalone | both (default: both)

AGENTAUTH_ACCESS_TOKEN
secret

Access token for AgentAuth MCP tool calls

MCP quality score · maturity, not trust · methodology
freshness
21
completeness
10
installability
25
documentation
15
stability
5
Alternatives in Other