Agent Trust MCP Server

Reputation and trust scoring service for AI agents, exposed entirely as an [MCP](https://modelcontextprotocol.io/) server. Evaluate counterparties

Local serverstdioPython

What is the Agent Trust MCP server?

Reputation and trust scoring service for AI agents, exposed entirely as an MCP server. Evaluate counterparties before transacting, report interaction outcomes, issue portable trust certificates, and. That is what the agent trust mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The tools it exposes

The server publishes 14 tools. What each one is for:

  • Discovery — The Discovery tool exposed by this server
  • discover — Returns the complete service catalog: available tools, auth methods, score types, interaction types, rate limits, and a quickstart guide. Call this
  • register_agent — 1. AgentAuth -- pass access_token from AgentAuth 2. Standalone -- pass your own public_key_hex (hex-encoded Ed25519 public key) 3
  • generate_agent_token — The generate_agent_token tool exposed by this server
  • whoami — The whoami tool exposed by this server
  • get_agent_profile — The get_agent_profile tool exposed by this server
  • search_agents — Search agents by trust score, capabilities, and interaction count
  • link_agentauth — Link an existing standalone profile to an AgentAuth identity, merging interaction history. The canonical agent_id after linking is always the
  • verify_link_proof — Preflight check: validate a link_agentauth proof without writing to the database. Runs the same validation steps (token authenticity, key lookup
  • agent_status — One-call status snapshot combining identity, trust scores, pending confirmation count, and active attestations. Useful as a dashboard or health check
  • check_trust — Primary tool for evaluating an agent before a transaction. Returns a score (0.0-1.0), confidence (0.0-1.0), interaction count, and a plain-language
  • check_trust_batch — The check_trust_batch tool exposed by this server

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

What it needs from you

Configuration is passed through the environment: AGENTAUTH_ACCESS_TOKEN, DATABASE_URL, REDIS_URL, SIGNING_KEY_PATH. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

  • Python 3.13+ - PostgreSQL 16 - Redis 7 - uv package manager

How it compares

Plenty of database access servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Agent Trust's toolset — Discovery, discover, register_agent and 11 more — is a fair guide to whether it matches your workflow. It is maintained by raditotev; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Agent Trust.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
DiscoveryThe Discovery tool exposed by this server.
discoverReturns the complete service catalog: available tools, auth methods, score types, interaction types, rate limits, and a quickstart guide. Call this first when connecting.
register_agent1. **AgentAuth** -- pass access_token from AgentAuth 2. **Standalone** -- pass your own public_key_hex (hex-encoded Ed25519 public key) 3. **Auto-generate** -- omit both to get a keypair generated for you
generate_agent_tokenThe generate_agent_token tool exposed by this server.
whoamiThe whoami tool exposed by this server.
get_agent_profileThe get_agent_profile tool exposed by this server.
search_agentsSearch agents by trust score, capabilities, and interaction count.
link_agentauthLink an existing standalone profile to an AgentAuth identity, merging interaction history. The canonical agent_id after linking is always the original standalone UUID — the AgentAuth UUID is stored as agentauth_id in met
verify_link_proofPreflight check: validate a link_agentauth proof without writing to the database. Runs the same validation steps (token authenticity, key lookup, proof signature, expiry, already-linked check) but never persists any chan
agent_statusOne-call status snapshot combining identity, trust scores, pending confirmation count, and active attestations. Useful as a dashboard or health check.
check_trustPrimary tool for evaluating an agent before a transaction. Returns a score (0.0-1.0), confidence (0.0-1.0), interaction count, and a plain-language explanation.
check_trust_batchThe check_trust_batch tool exposed by this server.
compare_agentsThe compare_agents tool exposed by this server.
get_score_breakdownDetailed Bayesian factors behind a score: raw score, dispute penalty, alpha/beta parameters, interaction weights.

How to install the Agent Trust MCP server

{
  "mcpServers": {
    "agent-trust": {
      "url": "https://agent-trust.radi.pro/mcp"
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Python 3.13+ - PostgreSQL 16 - Redis 7 - uv package manager
VariableDescriptionRequired
AGENTAUTH_ACCESS_TOKENCredential the server authenticates with.Yes
DATABASE_URLEndpoint or connection string the server talks to.Yes
REDIS_URLEndpoint or connection string the server talks to.Yes
SIGNING_KEY_PATHCredential the server authenticates with.Yes

Example prompts to try

  • Use Agent Trust to Discovery.
  • Use Agent Trust to discover.
  • Use Agent Trust to register agent.

Frequently asked questions

It connects Agent Trust to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (Discovery, discover, register_agent, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Agent Trust directly.