Model Context Protocol (MCP) Server Directory

Scale agent observability to billions of events with a ClickHouse APM MCP Server. Complete Python FastMCP implementation with sub-second span analytics.

MiniMax H3 is the first fully open omni-modal model generating 2K video with native stereo audio. This FastMCP server exposes its video, audio, and image generation capabilities to AI agents for automated media production pipelines.

NeMo Guardrails runs as a standalone Python library. This FastMCP server exposes it as a networked MCP tool, letting any agent validate outputs, detect injections, and enforce schemas without embedding guardrails code locally.

Firebase's official MCP server lacks Admin SDK operations. This FastMCP TypeScript server exposes Firestore queries, Auth user management, and Cloud Functions deployment to Claude Desktop and Cursor agents.

Deploy a Linear MCP server that lets AI agents autonomously plan sprints, triage issues, and manage project backlogs — reducing sprint planning time from 2 hours to 8 minutes while maintaining priority accuracy.

Deploy a Supabase Edge Functions MCP server that gives AI agents instant serverless backends — sub-50ms cold starts, built-in auth, and real-time database access via Model Context Protocol.

Deploy a Cloudflare D1 SQLite MCP server that gives edge-deployed AI agents persistent state with sub-5ms reads, automatic replication across 300+ edge locations, and zero cold-start overhead.

Vendor lock-in in vector databases traps agent memory in a single backend. This MCP server migrates agent memory between Qdrant, Pinecone, and Weaviate with zero downtime.

Agents that poll for new data waste 60% of their token budget on unchanged queries. This Kafka MCP Server pushes real-time events directly to agent workflows.

When your agent crashes at step 8 of a 12-step workflow, you lose everything. This Temporal MCP Server gives agents durable execution that survives crashes, deployments, and network failures.

Enterprise teams average 4,200 Notion pages per workspace, but AI agents cannot access them. This guide builds a Notion MCP server that indexes workspace content into a vector database, enables semantic search, and constructs knowledge graphs — giving Claude Desktop and Cursor full access to institutional knowledge.

MCP servers have hit 9,800+ on mcpservers.org, but observability MCP servers remain underbuilt. This guide builds a production Datadog MCP server that lets Claude Desktop and Cursor query APM traces, detect anomalies, and execute automated runbooks — reducing incident response time from 23 minutes to 90 seconds.