by aplavin · MCP Server · ★ 68
julia-mcp MCP server that gives AI assistants access to efficient Julia code execution. Avoids Julia's startup and compilation costs by keeping sessions alive across calls, and persists state (variables, functions, loaded packages) between them — so each iteration is fast. Sessions start on demand, persist state between calls, and recover from crashes — no manual management Each project directory gets its own isolated Julia process Pure stdio transport — no open ports or sockets Tools juliaeval(code, envpath?, timeout?) — execute Julia code in a persistent session.
| Stars | 68 |
| Forks | 12 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 74.0792867332492/100 |
| Open Issues | 5 |
| Last Updated | 2026-06-11 |
| Created | 2026-02-01 |
| Platforms | mcp, python |
| Est. Tokens | ~5k |
These tools work well together with julia-mcp for enhanced workflows:
Explore other popular mcp server tools:
julia-mcp is MCP server for persistent Julia sessions — fast iteration without startup/compilation overhead. It is categorized as a MCP Server with 68 GitHub stars.
julia-mcp is primarily written in Python. It covers topics such as ai, julia, llm.
You can find installation instructions and usage details in the julia-mcp GitHub repository at github.com/aplavin/julia-mcp. The project has 68 stars and 12 forks, indicating an active community.
julia-mcp is released under the MIT license, making it free to use and modify according to the license terms.