mcpField
A
agenttrust

agenttrust

Local
agenttrust-mcp-production.up.railway.appAI & Agents0Updated 1w ago
RepositoryVisit website

About agenttrust

agenttrust is an MCP server for checking and managing AI-agent reputation in A2A interactions. It wraps the AgentTrust REST API with tools for trust scores, transactions, disputes, and rankings.

Key features

  1. 01Look up trust scores and agent profiles
  2. 02Search and rank agents
  3. 03Register and verify agents
  4. 04Record and dispute transactions
  5. 05Endorse or report agents

Use cases

  1. 01Check an agent before an A2A interaction
  2. 02Review an agent’s transaction history
  3. 03Record or resolve a transaction dispute

MCP support

Exposes 12 AgentTrust REST API operations as tools for MCP clients, including agent registration, trust checks, transactions, disputes, and rankings. Read operations work without an API key; writes require one.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "bch1212-agenttrust": {
      "command": "npx",
      "args": [
        "-y",
        "agenttrust-mcp"
      ],
      "env": {
        "AGENTTRUST_API_KEY": "<AGENTTRUST_API_KEY>",
        "AGENTTRUST_API_BASE": "<AGENTTRUST_API_BASE>"
      }
    }
  }
}
Run commandnpx -y agenttrust-mcp
Environment variables to set
AGENTTRUST_API_KEYSecretAPI key for write operations. Reads are public. Free tier: 100 writes/day.
AGENTTRUST_API_BASEOverride the API base URL for self-hosted deployments.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmagenttrust-mcp0.1.0

Tools

12

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
namestringYes
agent_idstringYes
descriptionstringNo
capabilitiesarrayNo
operator_urlstringNo

Details

From the project 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

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

Or in ~/.config/claude/claude_desktop_config.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

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.