OpenAPITools SDK
@kvssankar
关于 OpenAPITools SDK
Your APIs, Now AI Tools. Build mcp servers in a minute.
基本信息
配置
工具
未检测到工具
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
概览
What is OpenAPITools SDK?
OpenAPITools SDK is a JavaScript package that enables developers to manage and execute tools across multiple AI API providers, including Anthropic’s Claude, OpenAI’s GPT models, and LangChain frameworks. It provides a unified interface for creating, accessing, and integrating tools as Python or Bash scripts.
How to use OpenAPITools SDK?
Install the package via npm: npm install @reacter/openapitools. Then use an adapter (e.g., AnthropicAdapter) in local mode or a ToolsAdapter with an API key in API mode. Tools are executed as subprocesses (Bash) or spawned threads (Python).
Key features of OpenAPITools SDK
- Unified interface for Claude, GPT, and LangChain integration
- Create tools as Python or Bash scripts with standardized I/O
- Local execution for full privacy and no external code transfer
- Supports both local mode (preferred) and API mode
- Bash tools are fast in Node.js; Python tools for complex packages
- Environment variables can be securely passed to tools
Use cases of OpenAPITools SDK
- Build interactive chatbots that use tools to solve complex tasks
- Run Python-based tools requiring packages like NumPy or Pandas
- Execute lightweight Bash tools for fast, scripted operations in Node.js
- Integrate custom tools with Claude, GPT, or LangChain AI assistants
- Manage and reuse tool definitions across different AI providers
FAQ from OpenAPITools SDK
How does OpenAPITools SDK compare to writing tools directly for each provider?
It provides a single SDK to define tools once and use them with Claude, GPT, and LangChain, rather than implementing separate integrations for each platform.
What are the runtime requirements?
Node.js is required for the JS package. Python tools need a Python interpreter installed; Bash tools require a Linux-compatible environment (tested on Linux or WSL, not Windows natively).
Where does tool execution happen and is my data secure?
All tool execution runs locally within your environment—no code is sent to external servers. Environment variables can be passed securely via input_json["openv"].
Are there any known limits or rate limits?
In API mode, rate limits apply (not specified further). Local mode has no network limits, but Python tools have interpreter startup overhead in JS.
What transports or authentication methods are supported?
Local mode uses file-system-based discovery (path to openapitools folder). API mode requires an API key (api_key="your_api_key"). No OAuth or alternate transports are mentioned.
开发工具 分类下的更多 MCP 服务器
Golf
golf-mcpProduction-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Runtime • Run real-world MCPs powering AI Agents
mcp-excalidraw
yctimlinMCP server and Claude Code skill for Excalidraw — programmatic canvas toolkit to create, edit, and export diagrams via AI agents with real-time canvas sync.
Deepwiki MCP Server
regenrek📖 MCP server for fetch deepwiki.com and get latest knowledge in Cursor and other Code Editors
MCP Framework
QuantGeekDevThe Typescript MCP Framework
test
harlancA simple,high performance and secure live media server in pure Rust (RTMP[cluster]/RTSP/WebRTC[whip/whep]/HTTP-FLV/HLS).🦀
评论