Refunc MCP Server
R

Refunc MCP Server

Refunc MCP Server is a Kubernetes-based function computing platform that supports multi-tool invocation through the SSE protocol.
2 points
9.0K

What is Refunc MCP Server?

Refunc MCP Server is a Kubernetes-based function computing platform that supports AI tool invocation through the SSE (Server-Sent Events) protocol. It allows developers to wrap a single function into multiple callable tools and interact through the standardized MCP protocol.

How to use Refunc MCP Server?

The basic usage process includes: 1) Deploy Refunc to the Kubernetes cluster. 2) Create functions and configure MCP events. 3) Invoke tools through the SSE endpoint. The entire process can be simplified using the refunc-cli tool.

Applicable scenarios

It is particularly suitable for scenarios where AI capabilities need to be encapsulated into standardized tools, such as chatbot plugin systems, intelligent decision-making nodes in automated workflows, and AI applications with multi-tool collaboration.

Main features

Single function, multiple tools
A single function can define multiple tool endpoints, and the call logic is distinguished by the _call_method parameter.
SSE protocol support
A standardized communication protocol based on Server-Sent Events, suitable for real-time interaction scenarios.
Parameter validation
Supports defining tool parameter formats through JSON Schema and automatically validates inputs.
Kubernetes native
Deeply integrated with Kubernetes, providing elastic scaling and resource management capabilities.
Advantages
Lightweight deployment with a Kubernetes-based standardized architecture
Flexible MCP protocol supporting multiple AI tool invocation modes
Developer-friendly operation experience provided by refunc-cli
Support for two mainstream languages, Python and Go
Limitations
The demonstration environment data is non-persistent and not suitable for direct production use
Currently only supports the x86_64 architecture
Requires basic Kubernetes knowledge for deployment and management
The SSE protocol has limited compatibility with some older browsers

How to use

Deploy Refunc
Deploy all components in the refunc-system namespace of the Kubernetes cluster.
Set up port forwarding
Expose the service locally for testing.
Create a function
Use refunc-cli to initialize and deploy a function.
Configure the MCP endpoint
Edit lambda.yaml to add MCP event configuration and update.

Usage examples

Create an Echo tool
Create a simple echo tool that returns the input content.
Multi-tool function
A single function implements two tools: translation and summarization.

Frequently Asked Questions

How to get the MCP SSE endpoint URL?
Which programming languages are supported?
How to implement persistent storage?

Related resources

Refunc CLI tool
The official command-line tool that simplifies function creation and management.
MCP protocol specification
The detailed technical specification of the Model Context Protocol.
Kubernetes deployment guide
The official Kubernetes documentation, providing the basics of cluster management.

Installation

Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

R
Rsdoctor
Rsdoctor is a build analysis tool specifically designed for the Rspack ecosystem, fully compatible with webpack. It provides visual build analysis, multi - dimensional performance diagnosis, and intelligent optimization suggestions to help developers improve build efficiency and engineering quality.
TypeScript
8.7K
5 points
N
Next Devtools MCP
The Next.js development tools MCP server provides Next.js development tools and utilities for AI programming assistants such as Claude and Cursor, including runtime diagnostics, development automation, and document access functions.
TypeScript
9.3K
5 points
T
Testkube
Testkube is a test orchestration and execution framework for cloud-native applications, providing a unified platform to define, run, and analyze tests. It supports existing testing tools and Kubernetes infrastructure.
Go
6.2K
5 points
M
MCP Windbg
An MCP server that integrates AI models with WinDbg/CDB for analyzing Windows crash dump files and remote debugging, supporting natural language interaction to execute debugging commands.
Python
9.5K
5 points
R
Runno
Runno is a collection of JavaScript toolkits for securely running code in multiple programming languages in environments such as browsers and Node.js. It achieves sandboxed execution through WebAssembly and WASI, supports languages such as Python, Ruby, JavaScript, SQLite, C/C++, and provides integration methods such as web components and MCP servers.
TypeScript
6.4K
5 points
P
Praisonai
PraisonAI is a production-ready multi-AI agent framework with self-reflection capabilities, designed to create AI agents to automate the solution of various problems from simple tasks to complex challenges. It simplifies the construction and management of multi-agent LLM systems by integrating PraisonAI agents, AG2, and CrewAI into a low-code solution, emphasizing simplicity, customization, and effective human-machine collaboration.
Python
6.1K
5 points
N
Netdata
Netdata is an open-source real-time infrastructure monitoring platform that provides second-level metric collection, visualization, machine learning-driven anomaly detection, and automated alerts. It can achieve full-stack monitoring without complex configuration.
Go
9.6K
5 points
M
MCP Server
The Mapbox MCP Server is a model context protocol server implemented in Node.js, providing AI applications with access to Mapbox geospatial APIs, including functions such as geocoding, point - of - interest search, route planning, isochrone analysis, and static map generation.
TypeScript
6.7K
4 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
21.6K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
31.1K
5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
61.9K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
18.9K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
26.9K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
58.4K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
18.8K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
42.2K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase