MCP Catalogs
← Home

julia-mcp

by aplavin·★ 63·Score 46

MCP server for persistent Julia sessions, avoiding startup costs and preserving state between calls.

developer-toolsai-llm
8
Forks
3
Open issues
this month
Last commit
2d ago
Indexed

Overview

The julia-mcp server provides AI assistants with efficient Julia code execution capabilities. It eliminates Julia's startup and compilation overhead by maintaining persistent sessions across multiple calls, preserving variables, functions, and loaded packages between iterations. Each project directory gets its own isolated Julia process, and the server uses pure stdio transport without requiring open ports or sockets.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:AI-assisted Julia development with fast code iteration
you:Scientific computing workflows requiring persistent state
you:Educational environments for teaching Julia programming
you:How does julia-mcp handle session persistence?
you:Can I use julia-mcp with AI clients other than Claude?

When to choose this

Choose julia-mcp when you need efficient Julia code execution with state persistence across multiple interactions, especially for Julia package development or scientific computing workflows.

When NOT to choose this

Avoid if you need Julia script execution with completely isolated runs or if you're working in an environment where Python is not available (the MCP server itself is written in Python).

Tools this server exposes

3 tools extracted from the README
  • julia_evaljulia_eval(code, env_path?, timeout?)

    Execute Julia code in a persistent session

  • julia_restartjulia_restart(env_path?)

    Restart a Julia session, clearing all state

  • julia_list_sessions

    List active Julia sessions and their status

Comparable tools

MCPRepl.jlREPLicant.jlDaemonConductor.jl

Installation

Installation

  1. Clone the repository:
git clone https://github.com/aplavin/julia-mcp.git
cd julia-mcp
  1. Register with Claude Desktop (add to claude_desktop_config.json):
{
  "mcpServers": {
    "julia": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/julia-mcp", "python", "server.py"]
    }
  }
}
  1. Prerequisites: Install uv and Julia (julia binary must be in PATH). Recommended packages: Revise.jl and TestEnv.jl.

FAQ

How does julia-mcp handle session persistence?
It keeps Julia sessions alive across multiple calls, preserving variables, functions, and loaded packages to avoid startup and compilation costs each time.
Can I use julia-mcp with AI clients other than Claude?
Yes, the documentation includes setup instructions for multiple clients including Codex CLI, VS Code Copilot, and GitHub Copilot Cloud Agent.

Compare julia-mcp with

julia-mcp vs ultimate_mcp_serverjulia-mcp vs mcp-server-chartjulia-mcp vs everythingjulia-mcp vs filesystemjulia-mcp vs time
GitHub →

Last updated · Auto-generated from public README + GitHub signals.