RLM Tools MCP Server

Your AI coding agent spends most of its token budget just reading your code - not reasoning about it. Every grep, file read, and glob result gets dumped into the conversation. On a large codebase, that's 25-35% of your context (and cost) burned on raw data the model never needed to see. It runs locally over stdio via the published package.

People connecting coding agent tools to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-02-13 · ★ 8 · #155 OF 194 MAINTAINED CODING AGENT · VERIFIED 2026-08-25

MIT · Python servers · how we verify → /methodology

01 · Install RLM Tools

before you install - you'll need

Set RLM_EVAL_PROJECT_PATH before connecting.

Claude Code

claude mcp add stefanoshea-rlm-tools -- uvx rlm-tools

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "stefanoshea-rlm-tools": {
      "command": "uvx",
      "args": [
        "rlm-tools"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package rlm-tools - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.stefanoshea is GitHub-verified and matches the repo owner

03 · Who maintains RLM Tools

RLM Tools is maintained by stefanoshea. It's the only MCP server we track from this author; the repo dates to Feb 2026.

04 · Facts

category
coding agent - ranked #155 of 194 actively-maintained coding agent servers as of 2026-08-25.
registry
io.github.stefanoshea/rlm-tools (active, first published 2026-02-13)
packages
pypi:rlm-tools

05 · RLM Tools FAQ

What is RLM Tools?

Your AI coding agent spends most of its token budget just reading your code - not reasoning about it. Every grep, file read, and glob result gets dumped into the conversation. On a large codebase, that's 25-35% of your context (and cost) burned on raw data the model never needed to see. It runs locally over stdio via the published package.

Is RLM Tools still maintained?

Yes - as of 2026-08-25, its last commit was 2026-02-13. We re-verify nightly.

How do I install RLM Tools?

Run `uvx rlm-tools`. The README documents one environment variable (RLM_EVAL_PROJECT_PATH) to set first. Set RLM_EVAL_PROJECT_PATH before connecting. You can also paste the ready-made client config above.

Does RLM Tools run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

06 · Alternatives to RLM Tools

More coding agent MCP servers · Code Nib · Plumb MCP · Pond · Vidin · Strem AI

More Python MCP servers · Memex (stifler7) · Adam Framework · Infra Node · DB MCP Server · Polar Health Data (self-hosted) · see all