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

@lyrie/mcp

v3.4.0

Published

Model Context Protocol (MCP) adapter for Lyrie Agent — connect to and host MCP servers

Readme

@lyrie/mcp

Model Context Protocol (MCP) adapter for Lyrie Agent. Lyrie.ai by OTT Cybersecurity LLC.

MCP is the open standard (modelcontextprotocol.io) that lets agents discover and call tools / resources / prompts from any compliant server. Lyrie speaks fluent MCP both as a client and as a server, so the entire MCP ecosystem becomes part of Lyrie's tool surface and Lyrie's own skills become callable from any other MCP-aware host.

This package gives Lyrie:

  1. Client mode — Lyrie connects to external MCP servers and registers their tools as Lyrie tools (auto-prefixed mcp:<server>:<tool>).
  2. Server mode — Lyrie exposes its own skills/tools as an MCP server so other MCP-aware agents can call into Lyrie.
  3. Configuration via the same JSON shape every MCP host uses (mcpServers in ~/.lyrie/mcp.json or lyrie.config.json).

Quick start (client mode)

import { McpClient } from "@lyrie/mcp";

const client = new McpClient({
  name: "filesystem",
  transport: { type: "stdio", command: "npx", args: ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"] },
});

await client.connect();
const tools = await client.listTools(); // [{name, description, inputSchema}, ...]
const result = await client.callTool("read_file", { path: "/tmp/hello.txt" });

Configuration file

~/.lyrie/mcp.json:

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"]
    },
    "github": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-github"],
      "env": { "GITHUB_PERSONAL_ACCESS_TOKEN": "${GITHUB_TOKEN}" }
    }
  }
}

Lyrie auto-discovers this file on boot when MCP is enabled in packages/core/src/config.ts.

Transports

| Transport | Status | |---|---| | stdio (subprocess) | ✅ supported | | http/sse (HTTP+SSE) | ✅ supported | | websocket | 🟡 planned |

Status

Ships in Lyrie v0.1.x. Wire-protocol implementation is intentionally minimal but spec-compliant; the goal is interoperability with the broader MCP ecosystem, not feature parity with any one host. Use bun run packages/mcp/src/index.ts list to verify a configured server responds.

License

MIT — © OTT Cybersecurity LLC. Lyrie.ai — https://lyrie.ai