Model Context Protocol (MCP) Server Directory

Nvidia's 88-core Vera CPU with custom Olympus cores delivers 1.8x speedup on agentic workloads. This FastMCP server exposes Vera's chiplet-aware scheduling, NVLink-C2C pairing, and LPDDR5X memory management to AI agents for production orchestration.

General Intuition, valued at $6B after tripling in 8 weeks, builds world models for predictive simulation. This FastMCP server exposes their simulation API to AI agents for causal inference, counterfactual analysis, and multi-step scenario planning before executing real-world actions.

Eliminate static credentials in agent workflows with HashiCorp Vault. Complete FastMCP TypeScript implementation with just-in-time token rotation and auto-revocation.

Debug multi-step agent trajectories with OpenTelemetry GenAI Semantic Conventions. Complete Python FastMCP implementation with live trace hierarchy and span bottleneck detection.

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.