How do I deploy the Refunc MCP Server?
Apply the Kubernetes manifest from the repository and port-forward the two services (`aws-api` and `mcp-server`) to local ports 8000 and 8001 respectively.
@refunc
基本信息
Refunc Model Context Protocol Server
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
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。
The Refunc MCP Server integrates Refunc serverless functions as tools in the Model Context Protocol (MCP), allowing you to expose functions as MCP endpoints via Server-Sent Events (SSE). It is designed for developers who want to create MCP-compatible tools from existing Refunc functions deployed on Kubernetes.
Deploy the Refunc components on Kubernetes using kubectl apply, then proxy the services locally. Install the refunc-cli and initialize a function with rfctl init. Edit the generated lambda.yaml to add an MCP event specification with a token and tool definitions. Finally, update the configuration with rfctl update-config and access the MCP SSE endpoint at the provided URL path.
refunc-cli to create and manage functions._call_method parameter.Apply the Kubernetes manifest from the repository and port-forward the two services (`aws-api` and `mcp-server`) to local ports 8000 and 8001 respectively.
The URL path format is `/namespace/<token-secret-name>/<token>/<func-name>/sse`. For the demo, it is `http://127.0.0.1:8001/refunc-system/mcp-demo/test/mcp-demo/sse`.
You need Python 3, the `refunc-cli` package installed via pip, and a Kubernetes cluster with the Refunc components deployed.
No, the data from the demo deployment is not persistent.
Define multiple entries under the `tools` array in the MCP event specification. Each tool requires a name, description, and JSON Schema for parameters. The function receives a `_call_method` parameter to identify which tool was invoked.
A search tool helps dev to solve the naming things problem.
Free moving quotes for AI agents from Next Generation Movers, a licensed interstate mover (USDOT 3764697). US long-distance nationwide and local DC/MD/VA. Indicative ballpark price and booking options; optional $0.01 x40
Open-source MCP to use Blender with any LLM

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
🚀 The fast, Pythonic way to build MCP servers and clients.
评论