Skip to main content
Glama

pixi-task

A secure MCP server providing controlled access to pixi tasks and commands, eliminating agent bash circumvention.

Overview

Exposes 11 pixi tools through 4 lean meta-tools (discover_tools, get_tool_spec, execute_tool, server_info) for ~95% context savings compared to a traditional MCP server that advertises every tool individually.

Two transports are supported:

  • stdio — exposes the full registry (11 tools).

  • HTTP — gates the surface to core + extended complexity (7 tools); use this for daemonised deployments. Default port: 4101.

Both transports surface a server_info meta-tool for self-identification (name, version, transport label, live tool counts, source URLs).

Related MCP server: MCP of MCPs

Development

pixi install -e quality
pixi run test
pixi run lint
pixi run format
pixi run typecheck

The HTTP server can be run directly:

pixi run http-server --port 4101

For background operation, the repo ships a systemd user unit at ~/.config/systemd/user/pixi-task.service.

Available Tasks

The canonical task list lives in [tool.pixi.tasks] in pyproject.toml. Key tasks:

Task

Purpose

test

pytest suite (timeout 30s)

test-cov

pytest with coverage

lint

ruff lint (F + E9 rules)

lint-full

full ruff lint

format

ruff format

typecheck

mypy on src/

quality

combined lint + format-check + typecheck

http-server

start the HTTP MCP transport

lean-server

start the stdio MCP transport

Run pixi task list to see every task.

License

MIT — see LICENSE.

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    Not graded
    maintenance
    A lightweight and fast MCP server that enables AI agents to efficiently discover and execute tools through progressive disclosure, minimizing context consumption while supporting safe code execution in external environments.
    3 npm
    -
  • A
    license
    Not graded
    quality
    D
    maintenance
    A meta-server that aggregates multiple MCP servers into a single interface, reducing token usage by 98%+ through progressive tool discovery and direct code execution that processes data between tools without consuming context window space.
    16 npm
    10
    Apache 2.0
  • A
    license
    A
    quality
    C
    maintenance
    An MCP server that sits between coding agents and local tools, using a tiny on-device model to route tool calls and requiring confirmations for destructive actions, while only exposing four tools to the host.
    4
    MIT
  • A
    license
    A
    quality
    C
    maintenance
    An MCP server that exposes 43 domain tools behind 4 meta-tools, applying guardrails such as budgets, rate limits, schema validation, human-in-the-loop confirmation for mutations, PII redaction, and an append-only audit log while reducing context window usage.
    4
    MIT