analog-mcp 0.2.0

Model Context Protocol server for Analog — expose webpage extraction to MCP-compatible AI agents.

analog-mcp

A Model Context Protocol server that exposes Analog's webpage-extraction engine to MCP-compatible AI agents — Claude Desktop, Cursor, and anything else that speaks MCP.

The headline tool is analog(url). Point it at a webpage; get back structured records (articles, pricing tables, product listings, etc.) already parsed into JSON. Same one-call shape as the Python SDK; same brand verb — analog is what your agent calls when it needs the content of a page in a form it can actually reason over.

Install

pip install analog-mcp

Or via uv:

uvx analog-mcp     # one-off
uv tool install analog-mcp

Sign in

analog-mcp installs the analog CLI alongside it. Sign in once:

analog login

This opens your browser, signs you in, and stores the key in your OS keyring — analog-mcp reads it from there, so no key ever lands in a config file. (Prefer to paste a key instead? Set ANALOG_API_KEY in the client's env block, as noted below.)

Configure your MCP client

Claude Desktop

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

{
  "mcpServers": {
    "analog": {
      "command": "analog-mcp"
    }
  }
}

Restart Claude Desktop. The analog tool will appear in the tool list. If you signed in with analog login, no env block is needed; to paste a key instead, add "env": { "ANALOG_API_KEY": "ak_..." }.

Cursor / other MCP clients

Same idea — the server command is analog-mcp and it speaks stdio. Refer to your client's MCP configuration docs for the exact file location.

Usage

Once configured, just ask the agent things like:

Extract the speakers from https://example-conference.com/2026

The agent calls analog(url=…) under the hood. The tool returns self-contained JSON with the parsed records plus a markdown rendering of the page, which the agent can then reason over directly.

What this version ships

analog-mcp 0.2.0 exposes a single tool — analog(url) — over the stdio transport. That's enough to cover the bulk of "give me the structured content of this page" use cases.

Planned for future versions:

• Additional tools for narrower queries
• SSE / streamable-HTTP transport for hosted/remote agents
• A [fetcher] extra that wires in JS-aware fetching for pages that need browser rendering (the install path exists today; the tool surface lands next)

License

MIT — see LICENSE.

Links

• Homepage: https://getanalog.io
• Python SDK: analog-sdk on PyPI
• JS-aware fetcher: analog-fetcher on PyPI