MCP Server Directory

Connect Claude to Microsoft Teams — read/send messages, list channels, search chats.

partreel io.github.mingyo186/partreel

Verified KiCad footprints, symbols & 3D models for AI agents. No signup, CC-BY-4.0, quality-gated.

Design tokens + a build prompt from any URL, right inside Claude Code, Cursor, and Codex.

Connect your Oura Ring to Claude AI assistants. Health metrics with smart analysis tools.

Write to Figma from any MCP client (Claude Code, Cursor). Complements the read-only official MCP.

MCP server for validating and generating SOUL.md agent identity files from Claude Desktop.

Alibaba Cloud DashScope MCP: Qwen chat, embeddings, and model discovery on your own account.

IBM watsonx.ai MCP by three.ws: chat, text generation, embeddings, and tokenization.

Bulge-tier financial model factory — live formulas, source-traced cells, 14 templates.

Query AI model benchmarks, pricing, and comparisons from rival.tips

WhichModel io.github.Which-Model/whichmodel

Cost-optimized LLM model routing recommendations for autonomous AI agents

MCP server for connecting Claude Code to a Hostinger VPS via SSH

Shared, project-aware memory for Claude Code, Codex, and other agents with human review.

Productivity-boosting RAG engine for codebases with multi-provider AI support and semantic search.

Fmp io.github.pipeworx-io/fmp

Financial Modeling Prep MCP (/stable API; v3 deprecated 2025-08-31).

Model multiplexer — route tasks to Codex, Gemini, and Claude CLIs with smart routing.

APIAny MCP server for model discovery, pricing, docs, and integration examples.

Persistent long-term memory for Claude Desktop / Claude Code, backed by EvolutionDB.

Biologically-inspired persistent memory engine for Claude Code MCP agents

Smart structured-data to TOON gateway: converts to TOON only when it saves LLM tokens.

GPU-accelerated MCP server for neural network training, deep learning, and model experimentation

Apple Foundation Models on-device. Generate, summarize, classify via Apple Intelligence.

Continuous behavioral drift monitoring for LLM apps — catches silent provider model updates.

Ping 134+ free coding LLMs across 17 providers, rank by latency, pick the fastest.