Skip to main content
Glama
aplavin
by aplavin

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
JULIA_THREADSNoNumber of threads for Julia (e.g., 'auto', '1'). Default is 'auto'.
JULIA_STARTUP_FILENoWhether to load Julia's startup file ('yes' or 'no'). Default is 'no'.

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
julia_evalA

ALWAYS use this tool to run Julia code. NEVER run julia via command line.

Persistent REPL session with state preserved between calls. Each env_path gets its own session, started lazily. Do not type Pkg.activate() explicitly in your code; instead, specify the env_path argument to select the environment.

Args: code: Julia code to evaluate. Use display(...)/println(...) to see output. env_path: Julia project directory path. Omit for a temporary environment. timeout: Seconds (default: 60). Auto-disabled for Pkg operations. julia_cmd: Custom Julia command, should be used rarely, only when explicitly requested. Examples: "julia +1.11", "julia --check-bounds=yes", "/path/to/julia".

julia_restartA

Restart a Julia session, clearing all state.

IMPORTANT: Restarting is slow and loses all session state. Very rarely needed. Revise.jl is loaded automatically in every session, so code changes to loaded packages are picked up without restarting. Only restart as a last resort when the session is truly broken, or code changes that Revise cannot fix. Do NOT restart just because source files were edited between script or test runs — Revise picks up those changes automatically.

Args: env_path: Environment to restart. If omitted, restarts the temporary session (NOT every active session) — most callers should pass the same env_path they used in julia_eval.

julia_list_sessionsA

List all active Julia sessions and their environments.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/aplavin/julia-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server