Skip to main content
Glama
Sign In
Python Dependency Manager Companion

Python Dependency Manager Companion

by KemingHe
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

⚠️ [Archived] ⚠️ Python Dependency Manager Companion MCP Server

WARNING

This repository is archived and no longer maintained.

  • Archived: 2026-02-15 by @KemingHe

  • Archive Reason: Use case too niche + better alternatives i.e. Context7 available

  • Inquries and Corrections: Email keminghe[dot]career[at]gmail[dot]com

Stop getting out-of-date Python package manager commands from your AI. Cross-reference latest official pip, conda, poetry, uv, pixi, and pdm docs with auto-updates. [Watch Demo on YouTube]

🚀 Quick Start for Agentic IDEs

1. Pull Docker image:

# Pin to commit hash for production security
# Get current hash from: https://hub.docker.com/r/keminghe/py-dep-man-companion/tags
docker pull keminghe/py-dep-man-companion@sha256:2c896dc617e8cd3b1a1956580322b0f0c80d5b6dfd09743d90859d2ef2b71ec6  # 2025-07-22 release example

# Or use latest for development
docker pull keminghe/py-dep-man-companion:latest

2. Add to your IDE's mcp.json:

{
  "mcp": {
    "servers": {
      "python-deps": {
        "command": "docker",
        "args": ["run", "-i", "--rm", "keminghe/py-dep-man-companion"]
      }
    }
  }
}

3. Ask package manager questions - "How to migrate a conda project to uv?" and get accurate, current official syntax.

Related MCP server: Software Management MCP Server

🤝 Contributing

Use as template: [Create from template] for your own MCP server projects.

Contribute back: Fork and follow CONTRIBUTING.md for development setup.

🔄 Auto-Update Architecture

  1. ⏰ Every Tuesday 6pm ET

  2. 📚 Sync Official Docs

  3. 🔍 Rebuild Search Index

  4. 🐳 Publish Latest Image

🗺️ Roadmap

  • Added support for pixi and pdm in version 0.1.1

  • Add comprehensive tests with 100% coverage

  • Add indexing support for PDF and CSV files

📁 Project Structure

python-dependency-manager-companion-mcp-server/
├── .github/workflows/            # Automation workflows
│   ├── auto-update-docs.yml      # Weekly docs update
│   ├── auto-update-index.yml     # Search index rebuild
│   ├── auto-update-publish.yml   # Multi-arch Docker publish
│   ├── auto-update.yml           # Combined automation
│   └── README.md                 # Workflow documentation
├── src/
│   ├── assets/               # Documentation source files
│   │   ├── conda/            # conda docs  
│   │   ├── pip/              # pip docs
│   │   ├── poetry/           # poetry docs
│   │   ├── uv/               # uv docs
│   │   ├── pixi/             # pixi docs
│   │   └── pdm/              # pdm docs
│   ├── index/                # Pre-built search index
│   ├── build_index.py        # Tantivy index builder
│   └── mcp_server.py         # FastMCP stdio server
├── Dockerfile                # Container build configuration
├── pyproject.toml            # Project dependencies and metadata
└── uv.lock                   # Locked dependencies

📄 License

This project is licensed under the MIT License - a permissive license that allows free use, modification, and distribution with attribution.

📞 Support

Open a GitHub issue for bug reports and feature requests.

Available Tools

1 tool
search_py_dep_man_docsB

Find comprehensive answers from latest official Python dependency manager documentation.

🎯 CORE VALUE: Access to authoritative, up-to-date official docs that general knowledge can't provide.

⚡ EXECUTION STRATEGY (85%+ first-call success):

  • MANDATORY: Multi-call progress report format:

    ### 📊 [Topic] Research - Progress Report [X]

- ✅ **Gathered**: [key findings]
- 🔄 **Next**: [specific gap]
- 🎯 **Goal**: [deliverable]

  • WHY: Users lose confidence without progress visibility; structured updates prevent confusion

  • WHEN: Use progress report format for ANY multi-step research (migration guides, comparisons, complex tutorials)

  • ENFORCEMENT: Show progress header AFTER EVERY INDIVIDUAL TOOL CALL, not just at final response (why: continuous user confidence)

  • TIMING: Tool call 1 → Progress Report 1 → Tool call 2 → Progress Report 2 → etc. → Final Answer (why: step-by-step transparency)

  • PATTERNS: Start with proven query patterns below for maximum hit rate

🎯 PROVEN QUERY PATTERNS (use these exact phrases for maximum results):

  • Learning: "project setup tutorial", "workflow guide", "dependency management guide" (why: comprehensive coverage)

  • Commands: "command reference", "syntax comparison", "installation commands" (why: precise syntax)

  • Comparing: "tool A vs tool B", "migration guide", "feature comparison" (why: structured analysis)

  • Troubleshooting: "troubleshooting guide", "common errors", "best practices" (why: solution-focused)

🧠 RESPONSE OPTIMIZATION RULES:

  • Specific question → focused query + top_n 3-5 + bullet format + show progress (why: targeted precision)

  • Broad/ambiguous → comprehensive query + top_n 7-10 + ranked list + track gaps (why: exploration needed)

  • Tool comparison → "X vs Y" + no filter + top_n 7-10 + scoring table + cite sources (why: comprehensive coverage)

  • Command help → expand terms + top_n 5-7 + code examples + update progress (why: actionable guidance)

📚 CITATION REQUIREMENTS (builds user confidence):

  • MANDATORY: Cite for commands, claims, comparisons, best practices, migration steps, troubleshooting advice (why: user confidence)

  • DENSITY: 1 citation per major section, 2-3 for complex guides/tutorials (why: consistent coverage)

  • FORMAT: "According to the official X guide" or "Command reference shows" (why: developer-friendly)

  • PLACEMENT: Immediately after stating command syntax, making performance claims, or giving advice (why: contextual validation)

  • PROGRESS INTEGRATION: Include citations naturally within progress updates to show source validation (why: transparency)

🚨 CRITICAL: Ground ALL responses in search results with citations (why: this tool's unique value over general knowledge).

Inputs: query (required), package_filter, top_n. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

    TDQS

    B3.3/5.0

    Scored across 1 tool

    Disambiguation5/5

    With only one tool, there is no possibility of confusion or overlap between tools. The tool has a single, clearly defined purpose: searching Python dependency manager documentation. No other tools exist to cause ambiguity.

    Naming Consistency5/5

    The single tool name 'search_py_dep_man_docs' follows a clear verb_noun pattern (search + py_dep_man_docs). Since there is only one tool, consistency is inherently perfect with no deviations or mixed conventions to evaluate.

    Tool Count2/5

    One tool is too few for a server named 'Python Dependency Manager Companion,' which suggests a broader scope like managing dependencies, not just searching docs. A single search tool feels thin and incomplete for the implied domain, lacking operations like installing, updating, or listing dependencies.

    Completeness2/5

    The tool surface is severely incomplete for the server's purpose. While the search tool is well-described, there are significant gaps: no tools for actual dependency management tasks (e.g., install, update, remove, list dependencies), version checking, or environment management. This will cause agent failures when trying to perform core dependency management workflows.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Resources

    Related MCP Connectors

    Related MCP Servers

    • Software Management MCP Server

      Bs4876
      F
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to automate local software management workflows including installation, uninstallation, updates, and environment recommendations. It provides a standardized, non-interactive interface for managing system applications and tracking software versions safely.
      -

    • MCPyDoc

      amit608
      A
      license
      Not graded
      quality
      D
      maintenance
      Provides real-time access to Python package documentation, source code, and symbol search to prevent AI hallucinations.
      271 PyPI
      7
      MIT

    • npmplus-mcp

      shacharsol
      A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI-powered JavaScript package management including search, install, update, remove, and security auditing across npm, yarn, and pnpm.
      75 npm
      9
      MIT

    Appeared in Searches