MCP-Compatible OpenAI Agents SDK
Hey HN, OpenAI released the Agents SDK yesterday, which is great because of its simplicity. I just added MCP support for it, which is currently available as a fork here: https://github.com/lastmile-ai/openai-agents-mcp (and on pypi as the openai-agents-mcp package). You can specify the names of MCP servers to give an Agent access to by setting its `mcp_servers` property. The Agent will then automatically aggregate tools from the MCP servers, as well as any `tools` specified, and create a single extended list of tools. This means you can seamlessly use MCP servers, local…
What it does
In the maker’s words, at launch
Hey HN, OpenAI released the Agents SDK yesterday, which is great because of its simplicity. I just added MCP support for it, which is currently available as a fork here: https://github.com/lastmile-ai/openai-agents-mcp (and on pypi as the openai-agents-mcp package). You can specify the names of MCP servers to give an Agent access to by setting its `mcp_servers` property. The Agent will then automatically aggregate tools from the MCP servers, as well as any `tools` specified, and create a single extended list of tools. This means you can seamlessly use MCP servers, local tools, OpenAI-hosted tools, and other kinds of Agent SDK tools through a single unified syntax -- and have them interact in the same Agent run loop! Everything else stays exactly the same. ``` agent = Agent( name="MCP Assistant", instructions="You are a helpful assistant with access to MCP tools.", tools=[your_other_tools], # Regular tool use for Agent SDK mcp_servers=["fetch", "filesystem"] # Names of MCP servers from your config file (see below) ) ``` The servers are configured in an `mcp_agent.config.yaml` file, very similar to how they are configured for Claude Desktop: ``` $schema: "https://raw.githubusercontent.com/lastmile-ai/mcp-agent/main..." mcp: servers: fetch: command: "uvx" args: ["mcp-server-fetch"] filesystem: command: "npx" args: ["-y", "@modelcontextprotocol/server-filesystem", "."] slack: command: "npx" args: ["-y", "@modelcontextprotocol/server-slack"] ``` I have submitted an issue and PR into the openai-agents-python repo [2], and my plan is instead of a fork, I will create an extension package for MCP support (coming later today). I was able to do this pretty quickly (got it working yesterday) because I've been building the mcp-agent library (https://github.com/lastmile-ai/mcp-agent), which makes MCP server aggregation/connection really easy. I did a Show HN about it a few weeks ago [3]. Wanted to share here to get community feedback on whether this is useful, which will help me decide if I should dedicate more time to it. [1] - https://github.com/lastmile-ai/mcp-agent [2] - https://github.com/openai/openai-agents-python/issues/23 [3] - https://news.ycombinator.com/item?id=42867050
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, March 2025
the whole month →
Mimic Human Research & Save Findings in AI Knowledge Base
AI · 2025 · sider.ai
