MCP HubMCP Hub
MCP·E218A6
I

claude-pytorch-treehugger

By izaitsevfb·Visit Source
Analytiques CI/CD PyTorch avec support MCP
18 avril 2025
Today
1 Clicks
About claude-pytorch-treehugger

Analytiques CI/CD PyTorch avec support MCP. claude-pytorch-treehugger is a Model Context Protocol (MCP) server maintained by izaitsevfb. It connects to MCP-compatible clients such as Claude Desktop, Cursor, Cline, and other agents that speak the protocol. It exposes 10 tools, including get_commit_summary, get_job_summary, get_filtered_jobs, get_failure_details, get_recent_commit_status, download_log_to_file, extract_log_patterns and extract_test_results, that an agent can call directly. It is categorized under AI/Analytics and Tool/Python.

Qu'est-ce que ce MCP

Ce MCP fournit une bibliothèque Python et un serveur pour interagir avec les données CI/CD de PyTorch via une API HUD, offrant un accès aux workflows, journaux de jobs et analytiques avec intégration ClickHouse.

Comment utiliser ce MCP

Installez via pip (pip install git+https://github.com/izaitsevfb/claude-pytorch-treehugger.git) et démarrez le serveur MCP avec python -m pytorch_hud. Utilisez des commandes CLI comme claude mcp add hud pytorch-hud pour vous connecter.

À quoi ce MCP peut servir

Analyser les pipelines CI/CD PyTorch, extraire des motifs de journaux, surveiller les résultats de tests, suivre l'utilisation des ressources et effectuer une analyse efficace des journaux pour des systèmes CI à grande échelle.

Repository Info
Stars:
4
Forks:
4
Watchers:
4
Last Updated: 3 months ago

AIMCP authority

DR and traffic signal for the AIMCP public domain.

FAQ

Frequently asked questions

What is the claude-pytorch-treehugger MCP server?

claude-pytorch-treehugger is a Model Context Protocol server from izaitsevfb. It lets MCP-compatible AI clients call its tools over a standard interface, so agents like Claude, Cursor, and Cline can use it without custom integration.

How do I connect claude-pytorch-treehugger to my AI client?

Add claude-pytorch-treehugger to your client's MCP configuration using the stdio or SSE connection shown in the usage examples on this page, then restart the client to load the server.

What tools does claude-pytorch-treehugger provide?

claude-pytorch-treehugger provides 10 tools: get_commit_summary, get_job_summary, get_filtered_jobs, get_failure_details, get_recent_commit_status, download_log_to_file, extract_log_patterns, extract_test_results, filter_log_sections and search_logs.

Is claude-pytorch-treehugger free to use?

claude-pytorch-treehugger is listed on AIMCP for free. Any API keys or accounts required by the underlying service are set by its provider.

Sponsored

Vernclaw Plugins for OpenClaw

Ready-to-use connectors for SEO data, social reading & content generation. Pay-as-you-go credits with audit logs.