MCP server for OpenAI Agents SDK documentation
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"openai-agents-sdk-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# OpenAI Agents SDK MCP Tool A Model Context Protocol (MCP) server that provides documentation for the OpenAI Agents SDK by extracting and indexing content from the official documentation website: https://openai.github.io/openai-agents-python/ This package can be installed as a Python library and used with any MCP-compatible LLM client (Claude Desktop, VS Code, Cursor, etc.). ## Installation ### From PyPI (Recommended) ```bash pip install openai-agents-sdk-mcp ``` ### From Source ```bash git clone https://github.com/gavinz0228/openai-agents-sdk-mcp.git cd openai-agents-sdk-mcp pip install -e . ``` See [INSTALLATION.md](INSTALLATION.md) for detailed installation instructions. ## Overview This project provides both a standalone CLI tool and an MCP server that allows LLMs to access and query the OpenAI Agents SDK documentation intelligently. ## Quick Start (MCP Server) 1. **Install the package**: ```bash pip install openai-agents-sdk-mcp ``` 2. **Set up API key** (Required): ```bash export OPENAI_API_KEY="sk-your-api-key-here" ``` Or create a `.env` file: ```bash cp .env.example .env # Edit .env and add your OpenAI API key ``` > **Important**: The tool requires an OpenAI API key to perform intelligent documentation matching. Without it, you'll see "No matching documentation found" errors. 3. **Configure your MCP client** (e.g., Claude Desktop): ```json { "mcpServers": { "openai-agents-sdk-docs": { "command": "openai-agents-sdk-mcp", "env": { "OPENAI_API_KEY": "sk-your-api-key-here" } } } } ``` 4. **Start using it** - Ask your LLM: - "List all OpenAI Agents SDK documentation topics" - "Get documentation for handoffs" - "How do I use streaming in OpenAI Agents?" See [INSTALLATION.md](INSTALLATION.md) and [MCP_CONFIGURATION.md](MCP_CONFIGURATION.md) for detailed setup instructions. ## Features ### 1. **MCP Server** (Primary Inte…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.