Browse 7,496 Model Context Protocol servers · MIT LicenseClear
Build complete Apps with our framework — study or fork this reference implementation. Covers all @mc
Build complete Apps with our framework — study or fork this reference implementation. Covers all @mc
Branchable LLM history DAG + encrypted context capsules agents can save, restore, and crypto-shred.
Privacy-first web analytics. Query pageviews, referrers, trends, and AI insights.
Portable AI memory as MCP tools: recall, read-only views, and one safe write.
Track AI agent costs, detect waste, optimize models, and prove ROI. 23 MCP tools across 10 domains.
Offload cheap work from your AI agent to a local Ollama model, at zero cloud cost.
AI bookkeeping agent for Japanese accountants — auto-classifies freee/Yayoi/MF/TKC transactions.
Fully local MCP server and CLI for web research
Shared, persistent memory for AI assistants, built on the Zettelkasten method.
AST-based Python refactoring MCP server with safe automated refactorings and rollback
Find & fetch research datasets across 12 archives, omics registries, and literature sources.
Self-hostable GPU-aware job broker: submit, route by VRAM, babysit jobs across machines via MCP.
Plant genomics MCP — 32 tools across 11 backends with cross-source synthesis.
Search 47,000+ marketing agencies and get AI-matched with fitted agencies, from Pick an Agency.
Self-hosted remote MCP memory server for ChatGPT and AI agents.
Semantic code graph MCP server for coding agents
Lets Claude Code or Codex CLI drive your real Chrome — sessions intact, 28 browser tools.
MCP server connecting Claude Code to GitHub for an issue to branch to PR to close workflow.
MCP server for tool discovery: find, compare, and verify tools across 35+ registries.
PDF native MCP server: generate, validate, sign PAdES, embed, extract. AI-powered.
Interact with Coda.io documents, tables, and rows via the Coda API
Asset planning, market data, econ releases, central bank speakers, US macro, geopolitical. 19 tools.
Persistent project memory for AI coding agents: one compact digest instead of re-reading the repo.