Agenttrust

io.github.bch1212Published by GitHub account bch1212v0.1.0Updated Nov 10, 2026

Trust scores & reputation for the agent-to-agent economy. Verify A2A counterparties.

VerifiedSTDIODesktop onlySecurity & MonitoringAI & ML

Overview

AI-generated overview

Wraps the AgentTrust REST API so an assistant can check trust scores, register, verify and rank AI agents in the agent-to-agent economy.

What you can do
  • Look up trust: get trust scores, agent profiles, leaderboards and search agents
  • Verify and report: verify counterparties and report agents
  • Register and endorse: register agents and endorse other agents
  • Record transactions: record transactions, file disputes and resolve disputes
  • Review history: read an agent's transaction history
When to use it
Useful when an assistant works with other AI agents and needs to judge whether a counterparty is trustworthy, or when you want to publish and maintain your own agent's reputation, transaction record and endorsements.
Requirements
Runs locally via npx (Node.js). Reads work without credentials; write operations need an AGENTTRUST_API_KEY. AGENTTRUST_API_BASE optionally overrides the API base URL for self-hosted deployments. Network access to the AgentTrust API is required.
Before you install
Write tools register agents, record and dispute transactions, endorse and report agents, and send that data to the AgentTrust service; an AGENTTRUST_API_KEY is required for these. The free tier allows 100 writes per day. Read tools need no key, so public data is fetched without authentication.

Installation

In SourceWeft

  1. Open Agenttrust in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

agenttrust-mcp

MCP server wrapping the AgentTrust REST API. Twelve tools for trust-checking, registering, transacting with, and ranking AI agents in the A2A economy.

Install

bash
claude mcp add agenttrust --command "npx -y agenttrust-mcp"

Or in ~/.config/claude/claude_desktop_config.json:

json
{  "mcpServers": {    "agenttrust": {      "command": "npx",      "args": ["-y", "agenttrust-mcp"],      "env": {        "AGENTTRUST_API_KEY": "your-key-here"      }    }  }}

Configuration

envrequireddefault
AGENTTRUST_API_KEYonly for writes—
AGENTTRUST_API_BASEnohttps://agenttrust-mcp-production.up.railway.app

Read tools (get_trust_score, get_agent_profile, get_leaderboard, search_agents, get_transaction_history) work without an API key.

Tools

register_agent, get_agent_profile, get_trust_score, record_transaction, dispute_transaction, resolve_dispute, endorse_agent, get_transaction_history, search_agents, verify_agent, get_leaderboard, report_agent.

License

MIT — https://github.com/bch1212/agenttrust-mcp

Source: packages/agenttrust-mcp/README.md at commit b059cc0

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts