fast-rlm MCP Server

How to use fast-rlm MCP Server

pip install fast-rlm

This is a recursive, no-carry-on design: each agent sees only the instruction its spawner handed it. A child does not inherit its parent's instruction, and the child's own `llm_query(...)` calls start fresh unless it passes `instruction=` again. There is intentionally no global, run-wide instruction.

Behavior:

- `instruction` must be a `str`. When omitted (`None`), nothing is appended and the prompt is unchanged.
- Because it is appended *after* the built-in prompt, a forceful instruction can override default behavior (e.g. output format or even the task itself). Keep it focused on *how* to answer rather than restating the task.
- `run(instruction=...)` is a per-call argument, not part of `RLMConfig`; pass it directly to `run(...)`. The in-REPL form is `llm_query(..., instruction=...)`.


## MCP servers

fast-rlm can connect to [Model Context Protocol](https://modelcontextprotocol.io) servers and expose their tools and resources inside the REPL. The agent calls them with `await mcp_call(server, tool, **kwargs)` and reads resources with `await mcp_read_resource(uri)` — just like any other REPL function.

**Nothing extra to install for fast-rlm.** MCP support is optional and lazy: 

What is fast-rlm MCP Server?

fast-rlm is a TypeScript MCP server for Cursor, Codex with npx, uvx/pip. A feature rich implementation of Recursive Language Models, with ACP integration, REPL tool support, structured IO, advanced visualization, logging tools. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.

Key capabilities

• Tool access support
• Shell commands support
• Spreadsheet work support
• Presentation work support
• Document generation support
• OpenAI provider support
• Anthropic provider support

Available tools

Technical details

Install or run fast-rlm using npx. Check avbiswas/fast-rlm for the latest setup command.

• Built for TypeScript
• Built for Node.js
• Built for Python
• Install or run with npx
• Install or run with uvx/pip
• Works with Cursor
• Works with Codex
• Uses stdio transport

Requirements and access

Security and permissions

Review permissions before connecting any MCP server to an agent. Pay special attention to whether it can read local files, write data, call external services, or perform destructive actions.

When to use fast-rlm MCP Server

• Use it for connecting agents to external tools and data.
• Use it for integrations workflows.
• Use it for coding workflows.
• Use it for data workflows.
• Use it for cursor users.

Built with

Explore related resources

Frequently asked questions