Skip to content
MCP server

Renyi

MCP toolchain server to check, format, run and test programs in the Renyi language

Runs locallyStatus and history
Install
Pricing
Open source
Platforms
CLI, Linux, macOS
Runs
Locally
Version
0.4.0
Listing updated
2 days ago

About Renyi

Renyi is an open-source MCP server for developer tools. It runs locally on your machine and is started by your AI client.

Renyi is a scripting language designed around code written by AI agents and reviewed by people. Each function's signature lists what it may do, such as filesystem.read or network access scoped to a host, and the compiler refuses anything undeclared. The signature of main acts as the grant for the whole program, and dependencies cannot widen it.

The MCP server is started with renyi mcp and runs over stdio. It gives an agent the toolchain: checking, formatting, running and testing programs, plus the project map showing effects, semantic diffs and chunks for embedding retrieval. Every compiler error carries a suggested fix, so the next attempt is more likely to be right. Runs can be recorded, replayed offline and explained.

The project is open source under Apache-2.0 and installs from release binaries for Linux, macOS and Windows or with cargo install renyi. A starter pack bundles a skill file, the MCP configuration and five workflows.

Install

Run in a terminal

claude mcp add renyi -- npx -y renyi

Add to claude_desktop_config.json

{
  "mcpServers": {
    "renyi": {
      "command": "npx",
      "args": [
        "-y",
        "renyi"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "renyi": {
      "command": "npx",
      "args": [
        "-y",
        "renyi"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "renyi": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "renyi"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "renyi": {
      "command": "npx",
      "args": [
        "-y",
        "renyi"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "renyi": {
      "command": "npx",
      "args": [
        "-y",
        "renyi"
      ]
    }
  }
}

What it does

Effects in signatures
Declares what a program may do, scoped and budgeted.
Check and run
Compiler refuses undeclared capabilities and suggests a fix.
Record and replay
Runs are recorded, replayed offline and explained.
Project map
Shows effects, semantic diffs and chunks for retrieval.
Dependency guard
Updates that widen effects are refused.
Starter pack
Skill file, MCP config and five workflows for agents.

Good for

  • Have an agent write automation scripts you can review from the signature
  • Replay a past run offline to see what it touched
  • Block a dependency update that adds new capabilities
  • Give a coding agent a toolchain with fix-bearing errors

Pricing

Open source

Apache-2.0

Prices change. Check renyi-lang.org before you buy.

Renyi FAQ

How is the MCP server started?

Run renyi mcp; the registry entry lists a stdio transport.

How do I install it?

Use the install script for Linux or macOS, the PowerShell script on Windows, or cargo install renyi.

What licence is it under?

Apache-2.0.

Is there a browser demo?

The site mentions a playground running the toolchain as WebAssembly.

Is Renyi free?

Yes. Renyi is open source, so you can use and self-host it for free.

How do I add Renyi to Claude Code?

Run this command in your terminal: claude mcp add renyi -- npx -y renyi

What are the best alternatives to Renyi?

The closest alternatives to Renyi are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Renyi

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools