🔌 API 集成 — Top 10 AI Agent 工具
连接第三方服务的万能插头：支付、地图、气象、翻译、发票……用标准 MCP 接口把外部 API 接进 AI 工作流，省掉手写 SDK 的时间，直接用自然语言调接口。
共收录 120 个工具 · 显示评分最高 10 个
webiny/webiny-js
精选TypeScriptOpen-source, self-hosted CMS platform on AWS serverless (Lambda, DynamoDB, S3). TypeScript framework with multi-tenancy, lifecycle hooks, GraphQL API, and AI-assisted development via MCP server. Built
microsoft/mcp
精选C#Catalog of official Microsoft MCP (Model Context Protocol) server implementations for AI-powered data access and tool integration
coddingtonbear/obsidian-local-rest-api
精选TypeScriptA secure REST API and Model Context Protocol (MCP) server for your vault.
claude mcp add --transport http obsidian https://127.0.0.1:27124/mcp/ \samanhappy/mcphub
精选TypeScriptA unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies.
docker run -p 3000:3000 -v ./mcp_settings.json:/app/mcp_settings.json -v ./data:/app/data samanhappy/mcphubWordPress/agent-skills
精选JavaScriptExpert-level WordPress knowledge for AI coding assistants - blocks, themes, plugins, and best practices
Zen4-bit/Proxima
精选JavaScriptMulti-AI MCP Server - Connect ChatGPT, Claude, Gemini & Perplexity to your coding tools without any API
agentic-community/mcp-gateway-registry
精选PythonEnterprise-ready MCP Gateway & Registry that centralizes AI development tools with secure OAuth authentication, dynamic tool discovery, and unified access for both autonomous AI agents and AI coding a
open-webui/mcpo
精选PythonA simple, secure MCP-to-OpenAPI proxy server
pip install mcpoknowsuchagency/mcp2cli
精选PythonTurn any MCP, OpenAPI, or GraphQL server into a CLI — at runtime, with zero codegen
mvanhorn/cli-printing-press
精选GoEvery API has a secret identity. This finds it, absorbs every feature from every competing tool, then builds the GOAT CLI — designed for AI agents first, with SQLite sync, offline search, and compound
go install github.com/mvanhorn/cli-printing-press/v4/cmd/cli-printing-press@latest💡 如何选择合适的 API 集成 工具？
评分是怎么算的？+
Trove 的评分包含 4 个维度：文档质量（Doc）、代码质量（Code）、社区活跃度（Community）和近期更新（Activity），总分 25 分，并划分为精选（≥20）、已验证（≥12.5）、社区（<12.5）三档。
如何选择适合自己的工具？+
先看 tier（精选/已验证优先），再看 stars 和近期更新时间，最后看 install_hint 确认安装方式是否符合你的环境（npm/pip/go 等）。
这些工具支持哪些 AI 平台？+
大多数工具以 MCP 协议为标准，兼容 Claude、OpenClaw、Codex、Cursor 等主流 AI 平台。部分工具还提供 OpenAI Function / LangChain Tool 格式。
如何把自己的工具上榜？+
在 GitHub 发布你的工具，带上相关 topic（如 mcp-server、ai-agent-skills），Trove 的爬虫会自动收录并评分。也可以到 opentrove.ai/publish 主动提交。