Skip to content

Latest commit

 

History

History

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

README.md

Tool Guides

Documentation for specific tools and integrations in IPFS Datasets Python.

MCP Server Tools (200+ Tools)

The MCP (Model Context Protocol) server provides 200+ tools across 49+ categories:

Web Scraping & Data Collection

Legal Data Tools

Web Search & APIs

Media Processing

  • FFmpeg Tools Integration - FFmpeg video/audio processing
  • Media download from 1000+ platforms (YouTube, Vimeo, TikTok, etc.)

Development Tools

Error Handling & Auto-Healing

Alerting & Notifications

Performance & Caching

Using Tools

Most tools can be accessed via:

1. Python API

import anyio

from ipfs_datasets_py.mcp_server.tool_registry import ToolRegistry

async def main():
	registry = ToolRegistry()
	tool = await registry.get_tool("development", "github_cli_status")
	result = await tool.execute({"install_dir": None})
	print(result)

anyio.run(main)

2. MCP Server

# Start MCP server
python -m ipfs_datasets_py.mcp_server

# Access via MCP protocol

3. CLI

# Enhanced CLI with all tools
python scripts/cli/enhanced_cli.py --list-categories
python scripts/cli/enhanced_cli.py [category] [tool] [args]

Tool Categories

  • dataset_tools - Dataset loading and processing
  • embedding_tools - Vector embeddings
  • search_tools - Search functionality
  • pdf_tools - PDF processing
  • media_tools - Multimedia processing
  • legal_dataset_tools - Legal data scraping
  • web_archive_tools - Web archiving
  • vector_tools - Vector store operations
  • ipfs_tools - IPFS operations
  • ...and 40+ more categories

Related Documentation