Model Context Protocol (MCP) Server Directory

Debugging Kubernetes clusters requires jumping between kubectl, Grafana dashboards, and logging tools. This FastMCP server consolidates cluster health, pod diagnostics, and resource optimization into a single MCP tool that AI agents can query directly from Claude Desktop or Cursor.

Gatik just raised $200M to scale driverless freight for PepsiCo, Walmart, and Tyson. This MCP server exposes autonomous freight tracking to AI agents with real-time ETA, route optimization, and exception management.

Google just launched Gemini Enterprise for Legal. This MCP server provides the backend tooling—clause extraction, due diligence checks, and regulatory compliance—for AI agents working in legal workflows.

AI coding agents write code in seconds but wait 8 minutes for CI feedback. This CircleCI MCP server bridges the gap—letting agents trigger pipelines, parse test failures, and auto-fix builds without leaving their IDE.

NVIDIA Jetson Orin Nano 2 powers millions of edge AI devices, but monitoring fleet health requires a native MCP server. This guide builds one with tools for device telemetry, inference status, battery management, and task assignment.

Multi-region agent deployments lose state on failover. CockroachDB's distributed SQL provides globally consistent agent state with automatic failover. This MCP server exposes CockroachDB to AI agents for transactional state management across regions.

Weaviate's vector database powers semantic search for agent RAG pipelines, but connecting it to MCP requires stateless-aware tool design. This guide builds a production Weaviate MCP server with hybrid search, reranking, and per-tenant collection isolation using the 2026-07-28 spec.

Okta's open-source MCP server introduces customization tools for AI clients. This FastMCP server extends Okta's identity governance to enforce least-privilege access for AI agents with real-time permission auditing.

Digital.ai's release MCP server enables AI agents to create release templates by understanding requirements and implementing best practices. This FastMCP server extends deployment automation with agent-driven release orchestration.

Laude Institute's Headlong harness runs autonomous agents at $1-2/hour in a continuous inner-monologue loop. This FastMCP server gives AI agents full lifecycle control over Headlong instances — start, monitor, checkpoint, and terminate with budget-aware cost tracking.

MCP 2026-07-28 drops session state for a stateless core, unlocking horizontal scaling on ordinary HTTP infrastructure. This Cloudflare Workers server implements the new spec for globally distributed agent tool access.

Amazon's Prime Air autonomous drones are expanding to 500 US cities. This FastMCP server exposes fleet management, delivery routing, and FAA airspace compliance APIs for AI agents to orchestrate autonomous last-mile delivery.