StepFun MCP Server

Introduction

⚠️ This project is for personal learning and communication purposes only.

This project is developed based on the capabilities provided by the StepFun Open Platform. Inspired by the implementation of MiniMax MCP, it builds an MCP (Multi-Modal Capability Provider) server compatible with the StepFun API.

Features

• ✅ Supports large language model (LLM) calls
• 🖼️ Supports visual language model (VLM) calls
• 🎨 Supports text-to-image generation
• 🎙️ Supports speech model capabilities

Quick Start

1. Installation

pip install stepfun-mcp
# or install from source:
# git clone git@github.com:weidafeng/StepFunMCP.git
# cd StepFunMCP
# pip install .

2. Configure MCP Server

Refer to the example configuration files:

• mcp_server_config_uvx_demo.json
• mcp_server_config_demo.json

Example config:

{
  "mcpServers": {
    "StepFun": {
      "command": "stepfun-mcp",
      "args": [],
      "env": {
        "STEPFUN_API_KEY": "YOUR_STEPFUN_API_KEY_HERE",
        "STEPFUN_API_HOST": "https://api.stepfun.com",
        "STEPFUN_MCP_BASE_PATH": "YOUR_OUTPUT_DIR",
        "STEPFUN_API_RESOURCE_MODE": "local"
      }
    }
  }
}

Communication & Collaboration

This project focuses on applying large models (LLMs/VLMs) in embodied intelligence and multi-agent systems. You're welcome to connect and discuss further:

• 📮 WeChat Official Account: Tristan
• 📘 Zhihu: Tristan

---

阶跃星辰 MCP server

简介

本项目仅供个人学习交流使用。

根据阶跃星辰开放平台StepFun提供的各种模型能力，仿照MiniMax MCP的实现，开发了一个基于stepfun api 的 MCP server。

功能特性

• 支持文本大模型调用
• 支持视觉理解大模型调用
• 支持文生图模型调用
• 支持语音模型调用

快速开始

1. 安装

pip install stepfun-mcp
# 或者
# git clone git@github.com:weidafeng/StepFunMCP.git
# pip install .

2. 配置mcp server config

可参考：mcp_server_config_uvx_demo.json 或者 mcp_server_config_demo.json

{
  "mcpServers": {
    "StepFun": {
      "command": "stepfun-mcp",
      "args": [
      ],
      "env": {
        "STEPFUN_API_KEY": "YOUR_STEPFUN_API_KEY_HERE",
        "STEPFUN_API_HOST": "https://api.stepfun.com",
        "STEPFUN_MCP_BASE_PATH": "YOUR_OUTPUT_DIR", 
        "STEPFUN_API_RESOURCE_MODE": "local"
      }
    }
  }
}

交流

本文持续关注VLM、LLM在具身智能、Agent中的应用，欢迎交流。

• 公众号：特里斯丹
• 知乎：特里斯丹