Model Context Protocol (MCP) Server Directory

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.

Sales teams spend 65% of their time on CRM data entry instead of selling. This guide builds a HubSpot MCP server that lets AI agents query deals, score leads, draft follow-ups, and automate pipeline management — giving Claude Desktop and Cursor direct CRM access for agentic sales orchestration.

Every AI agent you use has isolated memory. OzBrain's shared brain connects them all. This FastMCP Python server exposes read, write, search, and sync operations to any MCP-compatible agent — one brain, every agent.

Munder Difflin's multi-agent office needs an MCP interface. This FastMCP server exposes clone management, encrypted messaging, shared memory, and progress tracking to any MCP-compatible agent — enabling cross-tool orchestration of autonomous clones.

Agents need custom models trained on their specific tasks. This FastMCP server exposes Prime Intellect's full RL training pipeline — environment creation, hosted training, evaluation, and 1-click deployment — to any MCP-compatible agent.