Claude MarketplacesSubmit

Trust

agntor/mcp

This connects Claude, Cursor, and other MCP clients to Agntor's trust network for AI agents. You get 14 tools split across identity verification (agent cards, pulse checks, trust scores), security (guard_input for prompt injection, redact_output for PII), and commerce (escrow creation, x402 audit tickets). The guard_input tool scans prompts for injection attacks before they reach your agent, while tool authorization policies let you block or allow specific operations. Reach for this when you're building agent-to-agent workflows that need verifiable identity, payment rails, or runtime security checks. Runs over stdio for desktop clients or HTTP for hosted deployments, with optional API key auth.

tools: 14
auth: Secret needed
transport: STDIO
env vars: 2
last updated: Feb 16, 2026

Tools

14 tools

Public tool metadata for what this MCP can expose to an agent.

get_agent_cardRetrieve the verifiable AgentCard (Passport) for an agent

Retrieve the verifiable AgentCard (Passport) for an agent

No parameter schema in public metadata yet.

get_agent_registrationGet EIP-8004 compatible registration file for agent discovery

Get EIP-8004 compatible registration file for agent discovery

No parameter schema in public metadata yet.

check_agent_pulseGet real-time health and behavioral metrics

Get real-time health and behavioral metrics

No parameter schema in public metadata yet.

is_agent_certifiedQuick boolean check if an agent has valid certification

Quick boolean check if an agent has valid certification

No parameter schema in public metadata yet.

get_trust_scoreCalculate comprehensive trust score with behavioral factors

Calculate comprehensive trust score with behavioral factors

No parameter schema in public metadata yet.

register_agentRegister a new AI agent in the Agntor trust network

Register a new AI agent in the Agntor trust network

No parameter schema in public metadata yet.

verify_agent_identityTrigger verification (red-team probes) via the SDK

Trigger verification (red-team probes) via the SDK

No parameter schema in public metadata yet.

guard_inputScan incoming prompts for prompt injection and unsafe instructions

Scan incoming prompts for prompt injection and unsafe instructions

No parameter schema in public metadata yet.

redact_outputRedact PII, secrets, and sensitive content from outputs

Redact PII, secrets, and sensitive content from outputs

No parameter schema in public metadata yet.

guard_toolAuthorize or block tool execution with allow/deny policies

Authorize or block tool execution with allow/deny policies

No parameter schema in public metadata yet.

create_escrowCreate a new escrow task for agent-to-agent payment

Create a new escrow task for agent-to-agent payment

No parameter schema in public metadata yet.

issue_audit_ticketGenerate signed JWT ticket for x402 transactions

Generate signed JWT ticket for x402 transactions

No parameter schema in public metadata yet.

query_agentsSearch for agents by trust score, tier, capabilities

Search for agents by trust score, tier, capabilities

No parameter schema in public metadata yet.

activate_kill_switchEmergency disable an agent

Emergency disable an agent

No parameter schema in public metadata yet.

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly

Agent CaffeineSponsoredClose your lid, come back to finished work

SnugSponsoredThe clipboard manager for the AI era Promote your product hereReach 125k+ visitors monthly

WaxSponsoredBlock anything with supervision, without erasing your iPhone Promote your product hereReach 125k+ visitors monthly

knobsSponsoredSee your site on any phone, any day, in any language

Configuration

AGNTOR_API_KEYsecret

API key for Agntor backend calls (get one at app.agntor.com)

AGNTOR_SECRET_KEYsecret

JWT signing key for audit ticket generation

Readme

@agntor/mcp

MCP (Model Context Protocol) server for AI agent trust, discovery, and certification. Connects Claude, Cursor, VSCode, and any MCP-compatible client to the Agntor trust network.

Installation

npm install -g @agntor/mcp

Add to MCP Clients

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%/Claude/claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "agntor": {
      "command": "npx",
      "args": ["-y", "@agntor/mcp"]
    }
  }
}

Cursor

Open Cursor Settings
Go to Features > Model Context Protocol
Add new server:
- Name: Agntor Trust
- Command: npx
- Args: -y @agntor/mcp

Cline (VSCode Extension)

Edit ~/.cline/mcp.json:

{
  "mcpServers": {
    "agntor": {
      "command": "npx",
      "args": ["-y", "@agntor/mcp"]
    }
  }
}

Continue (VSCode Extension)

Edit ~/.continue/config.json:

{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "name": "agntor",
        "command": "npx",
        "args": ["-y", "@agntor/mcp"]
      }
    ]
  }
}

Quick Start

View the full README on GitHub

Details

Repository: github.com/agntor/mcp
Package: @agntor/mcp
Transport: STDIO
Auth: Required
Registry: MCP registry, active