Model Context Protocol (MCP) Server Directory

AI agents need instant access to web analytics. This FastMCP server exposes Vercel Analytics and Edge Config data to Claude and Cursor, querying 50 million page views in under 3 seconds.

AI agents need project management access. This FastMCP server exposes Linear issue tracking to Claude and Cursor, autonomously triaging 500 issues per hour with 94% accuracy.

AI agents need live database access. This FastMCP server streams Supabase Realtime changes, invokes Edge Functions, and queries pgvector — giving Claude and Cursor instant access to live application data.

Slack launched an official remote MCP server supporting search, messaging, canvases, and user management over Streamable HTTP. This FastMCP TypeScript server extends that capability with enterprise features: channel-specific AI assistants, automated standup summaries, and canvas-based knowledge management.

Sprint planning consumes 2-4 hours per sprint for a 10-person team. This FastMCP Python server connects AI agents to Jira, enabling autonomous backlog analysis, priority scoring based on business value and dependency graphs, story point estimation from historical velocity, and sprint plan generation.

ATTOM Data expanded its AI platform in August 2026 with specialized agents and an MCP server. This FastMCP TypeScript server wraps ATTOM's 150M+ property records into 7 agent-callable tools for automated property valuation, market analysis, investment screening, and neighborhood intelligence.

GitHub Enterprise rolled out strict MCP allowlists in August 2026, requiring enterprises to explicitly approve which MCP tools Copilot agents can access. This FastMCP Python server implements the allowlist enforcement layer, logging every tool call, blocking unauthorized access, and generating compliance reports.

Cloudflare's Agents Week 2026 launched WebMCP, making any Cloudflare-proxied site agent-accessible. This FastMCP TypeScript gateway extends that capability to ALL websites, not just Cloudflare ones, by wrapping Playwright browser automation into MCP tools that any AI agent can call.

Marketing teams spend 12+ hours weekly creating repetitive social media designs. This FastMCP TypeScript server connects AI agents to Canva's Connect API, enabling autonomous batch design generation, template filling, brand kit enforcement, and export—all from Claude Desktop or Cursor.

Most FastMCP servers crumble past 50 concurrent sessions because they share a single event loop. This worker pool architecture isolates sessions, enforces per-session rate limits, and handles 500 concurrent agent sessions with sub-100ms P99 latency using Python multiprocessing and Redis-backed session state.

Enterprise teams store 80% of their institutional knowledge in Notion—but AI agents can't access it. This FastMCP TypeScript server exposes Notion pages, databases, and wikis to Claude Desktop and Cursor agents with semantic search, auto-summarization, cross-database joins, and incremental indexing that keeps knowledge fresh without API rate limit exhaustion.

Cerebras CS-4 delivers 30x faster inference than NVIDIA Blackwell by processing on a full 300mm wafer. This FastMCP server wraps Cerebras' API, giving Claude Desktop and Cursor agents sub-100ms token generation for latency-critical tool calls.