Top · MCP-25
The 25 best MCP servers.
Model Context Protocol (MCP) is Anthropic's open standard for letting AI agents call external tools. These are the most-used MCP servers — drop them into Claude Desktop, Cursor, or any MCP-aware client.
Read the full MCP-25 index or jump to comparison.
| # | Agent | 24h | Score | Δ24h |
|---|---|---|---|---|
| 1 | open-webui open-webui: User-friendly AI Interface (Supports Ollama, OpenAI API, ...) | 58.1 | 0.00 | |
| 2 | dify dify: Production-ready platform for agentic workflow development. | 8 | 53.2 | +1.14 |
| 3 | graphify graphify: Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store. | 4 | 53.1 | -1.48 |
| 4 | OmniRoute OmniRoute: Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% t... | 1 | 52.4 |
Common questions
- What is MCP?
- Model Context Protocol — an open standard from Anthropic that lets AI agents connect to tools (files, GitHub, databases, browsers) over a clean interface. See modelcontextprotocol.io for spec.
- Are these audited?
- AgentTape doesn't audit MCP servers. Read the source before connecting any MCP server to a session that has access to data you care about. Most are MIT-licensed and on GitHub.
Methodology and source code are public — read how AgentScore works.