Schema | AgentTrust

AgentTrust

Describes the environment variables required to run the server.

Name	Required	Description	Default
`MCP_PORT`	No	Port for HTTP transport (default: 8000)	8000
`JSON_LOGS`	No	Output logs in JSON format (default: false)	false
`LOG_LEVEL`	No	Logging level (default: INFO)	INFO
`REDIS_URL`	No	Redis connection string (e.g., redis://localhost:6379/0)	redis://localhost:6379/0
`ENVIRONMENT`	No	Environment: 'development' or 'production' (default: development)	development
`DATABASE_URL`	No	PostgreSQL connection string (e.g., postgresql+asyncpg://agent_trust:agent_trust@localhost:5432/agent_trust)	postgresql+asyncpg://agent_trust:agent_trust@localhost:5432/agent_trust
`AUTH_PROVIDER`	No	Authentication provider: 'agentauth', 'standalone', or 'both' (default: both)	both
`MCP_TRANSPORT`	No	MCP transport: 'stdio' or 'streamable-http' (default: stdio)	stdio
`DISPUTE_PENALTY`	No	Penalty applied to score for upheld disputes (default: 0.03)	0.03
`SIGNING_KEY_PATH`	No	Path to the server's Ed25519 signing key file (e.g., keys/service.key)	keys/service.key
`AGENTAUTH_MCP_URL`	No	URL of the AgentAuth MCP server	https://agentauth.radi.pro/mcp
`SCORE_HALF_LIFE_DAYS`	No	Half-life for exponential time decay of interaction weights (default: 90)	90
`ATTESTATION_TTL_HOURS`	No	Default time-to-live for attestations in hours (default: 24)	24
`AGENTAUTH_ACCESS_TOKEN`	No	Access token for registering scopes with AgentAuth (optional for self-hosting)

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/raditotev/agent-trust'

If you have feedback or need assistance with the MCP directory API, please join our Discord server