InfiniteMCP
A meta-MCP server that acts as a universal gateway, allowing users to discover and execute tools from thousands of other MCP servers through semantic search. It dynamically loads servers on demand and provides standardized functions for searching, discovering, and running tools across the entire MCP ecosystem.
README
InfiniteMCP
A meta-MCP server that gives Claude access to the entire ecosystem of MCP servers through semantic search and dynamic tool discovery.
What is InfiniteMCP?
InfiniteMCP is a Model Context Protocol (MCP) server that acts as a universal gateway to thousands of other MCP servers. Instead of manually configuring each MCP server you want to use, InfiniteMCP lets Claude discover, understand, and use any MCP server on demand through natural language queries.
Think of it as an "MCP server of MCP servers" - a single connection that unlocks the entire MCP ecosystem.
How It Works
Claude asks: "Search for MCP servers that can crawl websites"
↓
InfiniteMCP searches 1000+ indexed MCP servers
↓
Returns: [firecrawl-mcp, web-scraper-mcp, playwright-mcp, ...]
↓
Claude: "Use firecrawl to get content from example.com"
↓
InfiniteMCP dynamically loads firecrawl-mcp and executes the request
↓
Returns the crawled content to Claude
The Three Core Functions
InfiniteMCP exposes three powerful tools to Claude:
-
search_mcp- Semantic search across all known MCP serversInput: "web search" Output: [brave-search-mcp, tavily-mcp, serper-mcp, ...] -
get_functions- Discover what an MCP server can doInput: mcp_id (e.g., "brave-search-mcp") Output: [brave_web_search, brave_local_search, ...] -
run_function- Execute a function from any MCP serverInput: mcp_id, function_name, arguments, credentials Output: Function result
Features
- 🔍 Semantic Search - Find MCP servers using natural language, powered by state-of-the-art embedding models
- 🚀 Dynamic Loading - MCP servers are loaded on-demand, no pre-configuration needed
- 🔐 Smart Credential Management - Securely handles API keys and credentials, with user prompts for missing values
- 🧩 Tool Discovery - Automatically discovers all available functions from any MCP server
- 📚 Comprehensive Index - Pre-indexed with 1000+ MCP servers from the ecosystem
- ⚡ Efficient - Caches connections and metadata for fast repeated access
Installation
Prerequisites
- Python 3.11+
- CUDA-capable GPU (recommended for embedding search)
- Node.js 18+ (for running discovered MCP servers)
Setup
Local install will try a cuda and fallback to cpu
# Clone the repository
git clone https://github.com/yourusername/infinitemcp.git
cd infinitemcp
# Install dependencies
pip install -r requirements.txt
# Build the MCP server index (one-time setup)
./extracto
Usage
With Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"infinitemcp": {
"command": "python",
"args": ["-m", "infinitemcp"],
"env": {
"INFINITEMCP_DB": "/path/to/infinitemcp/db"
}
}
}
}
Example Interactions
Discovering servers:
You: "I need to search the web for information about MCP servers"
Claude: [uses search_mcp("web search")]
Claude: "I found several options. Brave Search looks good. Let me use that..."
Using a server:
Claude: [uses get_functions("brave-search-mcp")]
Claude: [uses run_function with brave_web_search]
Claude: "Here's what I found..."
Handling credentials:
Claude: [attempts run_function("github-mcp", ...)]
InfiniteMCP: "Missing required credential: GITHUB_TOKEN"
Claude: "I need your GitHub token to access that API..."
You: "Here it is: ghp_..."
Claude: [retries with credentials]
Architecture
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.