Log inSubmit server
Agntor MCP logo

Agntor MCP

by agntor

Audits, protects, discovers, and administers AI agents through trust, certification, escrow, and safety tools.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Agntor MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "agntor-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@agntor/mcp"
      ],
      "env": {
        "AGNTOR_API_KEY": "YOUR_VALUE_HERE",
        "AGNTOR_MCP_AUTH_KEY": "YOUR_VALUE_HERE",
        "AGNTOR_SECRET_KEY": "YOUR_VALUE_HERE",
        "AGNTOR_API_URL": "YOUR_VALUE_HERE",
        "PORT": "YOUR_VALUE_HERE",
        "MCP_TRANSPORT": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

npx -y @agntor/mcp

No response to initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked .

Overview

The agntor/mcp MCP server connects MCP clients to the Agntor trust network for agent discovery, certification, safety checks, and payments. It exposes 14 tools over stdio or HTTP, with REST API calls handled through the Agntor backend and selected guard utilities running locally. Use it when an agent workflow needs identity checks, trust scoring, prompt and output protection, tool authorization, escrow, or emergency agent controls. API-backed features use Agntor credentials, while the server can also be reached through the hosted endpoint at https://mcp.agntor.com/mcp.

Use cases

  • Check whether an agent has valid certification before delegation
  • Scan prompts for injection and unsafe instructions
  • Redact sensitive information from model outputs
  • Authorize or block tool calls with policies
  • Create escrow tasks for agent-to-agent payments

Key features

  • Agent discovery and registration
  • Certification and trust scoring
  • Prompt, output, and tool safety controls
  • Escrow and signed x402 audit tickets
  • Agent search and emergency kill switch
  • Stdio and HTTP MCP transports

Tools14

What Agntor MCP lets your agent do. Expand a tool for its parameters.

Self-reported~238 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked

Recent health check succeeded.

23/23 checks healthy over the last 95d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 9d ago via OSV.dev · @agntor/mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars1Stargazers on the source repository.
npm downloads176Package downloads in the last 30 days.
Last commit9mo agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.
Tools exposed14Callable tools this server registers over MCP.
Directory activity4 viewsConfig copies, upvotes, and views on AllMCPs.

How Agntor MCP works

What agntor/mcp MCP server does

The agntor/mcp MCP server exposes Agntor’s agent trust and administration functions to MCP-compatible clients. Its tools cover four main areas: discovering and evaluating agents, guarding agent interactions, supporting agent-to-agent payments, and managing registered agents.

For discovery and certification, clients can retrieve an AgentCard, fetch an EIP-8004-compatible registration file, inspect health and behavioral metrics, check certification status, calculate a trust score, register an agent, and trigger identity verification through the SDK. The security tools scan incoming prompts for prompt injection and unsafe instructions, redact PII or secrets from outputs, and apply allow or deny policies to tool execution.

Payment-related operations include creating escrow tasks and issuing signed JWT audit tickets for x402 transactions. Administrative tools can search agents by trust score, tier, or capabilities and activate an emergency kill switch for an agent.

How it works

The agntor/mcp MCP server communicates with clients through the MCP protocol using either stdio or HTTP.

The server uses local SDK utilities for guarding input, redacting output, and enforcing tool policies. Trust, identity, discovery, and related backend operations call the Agntor REST API through the SDK. Applications can also import createAgntorMcpServer and connect the resulting server to an HTTP, stdio, WebSocket, or another transport.

Setup and configuration

Install the package globally with npm or run it directly from an MCP client using npx -y @agntor/mcp. The client configuration uses npx with the package name and the -y flag. Standalone stdio mode is available with the package’s --stdio option.

HTTP operation uses AGNTOR_API_KEY and AGNTOR_SECRET_KEY in the documented startup example. AGNTOR_API_KEY is required for API tools. AGNTOR_MCP_AUTH_KEY protects the HTTP MCP endpoint and falls back to the API key when it is not set. The backend URL defaults to https://app.agntor.com, and the HTTP server defaults to port 3100. MCP_TRANSPORT can force the transport mode, including stdio.

The hosted endpoint is https://mcp.agntor.com/mcp. When authentication is enabled there, requests include the X-AGNTOR-API-KEY header.

Tools and capabilities

The 14 exposed tools include:

  • Agent identity and trust: get_agent_card, get_agent_registration, check_agent_pulse, is_agent_certified, get_trust_score, register_agent, and verify_agent_identity.
  • Safety controls: guard_input, redact_output, and guard_tool.
  • Commerce and audit: create_escrow and issue_audit_ticket.
  • Administration: query_agents and activate_kill_switch.

The agntor/mcp MCP server therefore fits workflows that need to inspect an agent before delegation, screen model inputs and outputs, authorize tools, create payment arrangements, or disable an agent during an incident.

Limitations and notes

API-backed operations depend on Agntor credentials and its backend service. HTTP authentication is described as conditional, while the API key is explicitly required for API tools. The repository is licensed under MIT.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Agntor MCP

Run it with `npx -y @agntor/mcp`, or install the package globally with `npm install -g @agntor/mcp`.

Yes. The README provides Claude Desktop configuration using `npx` and `-y @agntor/mcp`.

`AGNTOR_API_KEY` is required for API tools. HTTP endpoint authentication can use `AGNTOR_MCP_AUTH_KEY`, which falls back to `AGNTOR_API_KEY`.

Yes. The `guard_input` tool scans incoming prompts for prompt injection and unsafe instructions.

Yes. It supports HTTP mode locally and provides the hosted endpoint `https://mcp.agntor.com/mcp`.

Related MCP servers

All in Security All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewAgntor MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/agntor-mcp?style=directory)](https://allmcps.com/mcp/agntor-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/agntor-mcp"><img src="https://allmcps.com/api/badge/agntor-mcp?style=directory" alt="Agntor MCP on AllMCPs" /></a>