npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@agentmark-ai/mcp-server

v0.4.2

Published

MCP server for AgentMark trace debugging

Readme

@agentmark-ai/mcp-server

MCP (Model Context Protocol) server for AgentMark. Exposes the full AgentMark API to AI editors like Claude Code and Cursor: list traces and drill into spans, append dataset rows, write scores, run experiments, manage apps, deployments, environments, alerts, and annotation queues.

How it works

The server doesn't ship a fixed, hand-written tool list. On startup it reads the gateway's OpenAPI contract from <AGENTMARK_API_URL>/v1/openapi.json and registers one MCP tool per endpoint — tool names are the spec's operationIds in snake_case (list_traces, get_trace, create_score, append_dataset_row, create_app, ...). The tool surface always matches what the gateway actually accepts.

Both the local agentmark dev server and the Cloud gateway serve the same OpenAPI contract, so the same binary works against either — only the configured URL differs.

Usage

Run it with npx; there's nothing to install. npm create agentmark@latest wires this up for you (as the agentmark and agentmark-local entries); the configs below are the manual equivalent.

Local dev server (Claude Code, Cursor, etc.)

Point at your running agentmark dev server. Add to .mcp.json (Claude Code), .cursor/mcp.json (Cursor), or your editor's MCP config:

{
  "mcpServers": {
    "agentmark-local": {
      "command": "npx",
      "args": ["-y", "@agentmark-ai/mcp-server"],
      "env": {
        "AGENTMARK_API_URL": "http://localhost:9418"
      }
    }
  }
}

Local calls are unauthenticated — no key needed.

AgentMark Cloud

After agentmark login, no key is needed: the server resolves your session from ~/.agentmark/auth.json and refreshes it automatically. For CI or agents without a login session, supply an API key (it takes precedence over the session):

{
  "mcpServers": {
    "agentmark": {
      "command": "npx",
      "args": ["-y", "@agentmark-ai/mcp-server"],
      "env": {
        "AGENTMARK_API_KEY": "your-api-key"
      }
    }
  }
}

Configuration

| Environment Variable | Default | Description | |---------------------|---------|-------------| | AGENTMARK_API_URL | https://api.agentmark.co | Gateway URL; set to http://localhost:9418 for the local dev server | | AGENTMARK_API_KEY | - | API key for Cloud authentication (optional after agentmark login; local dev is unauthenticated) | | AGENTMARK_TIMEOUT_MS | 30000 | Per-request timeout in milliseconds |

Requirements

For local development:

  1. The AgentMark CLI installed and running (agentmark dev)
  2. Traces recorded in your local AgentMark database

Programmatic Usage

import { createMCPServer, runServer } from '@agentmark-ai/mcp-server';

// Run the server with stdio transport
await runServer();

// Or create a server instance for custom transport
const server = await createMCPServer();

Documentation

Full reference at docs.agentmark.co/reference/mcp-servers.

License

AGPL-3.0-or-later