66,561 MCP Servers, Scored and Updated Daily

USPTO patent search and prior art lookup. Not legal advice

Can this LLM run on my GPU? VRAM, speed ceiling and what fits instead, for any model and GPU.

One identity an AI agent owns: proves who it is offline, keeps its reputation, pays, messages agents

Managed LinkedIn MCP server for AI agents: search, connect, message and enrich on accounts you own.

Compress coding-agent context ~64%. Hosted Neural Keep MCP for Cursor/Claude/Codex.

Sap Mcp Server

Official MCP gateway for OOBE Protocol SAP — AI agents can interact with SAP identity, registry, reputation, tools, memory, payments, settlement, and proof-of-execution on Solana

Alza MCP

Unofficial MCP server for Alza.cz: catalog search plus token-guarded account and checkout.

Start, stop and read logs of your local dev servers from Claude Code, Cursor and Codex.

Eventbrite for Claude — your tickets/orders, organizer data, and public event discovery

Free x402 preflight gate plus paid on-chain truth checks for AI agents.

AgentRecall MCP

Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.

Self-hosted memory for LLMs in TriliumNext, structured by the server and editable by you.

Deploy durable AI agents with Omnara, an open-source managed-agent platform.

Open automation engine for AI agents. Control live browsers and desktop apps locally.

Detect fabrication and hallucination in any LLM output. 30+ models supported.

Let AI agents use secrets without seeing them: inject into a command, redact the output.

Memory for AI agents: persistent L1/L2/L3, web-search savings, thread memory.

Policy checks for AI agent writes (ALLOW/DENY/STEP_UP) with a tamper-evident audit log.

Compliance-filtered crypto exchange fee comparison and rebate-link routing for AI agents.

Local-first MCP memory: Markdown notes and images with full-text search for Claude and Cursor.