mcpField
阶
阶跃星辰 MCP server

阶跃星辰 MCP server

Local
github.com/weidafengAI & Agents1Updated 26w ago
Repository

About 阶跃星辰 MCP server

阶跃星辰 MCP server is an MCP server built on the StepFun open platform API for personal learning and exchange. It makes text, vision, image-generation, and speech model capabilities available to MCP clients.

Key features

  1. 01Call text models
  2. 02Call vision models
  3. 03Call text-to-image models
  4. 04Call speech models

Use cases

  1. 01Call a text model from an MCP client
  2. 02Analyze image content
  3. 03Generate images from text
  4. 04Use speech model capabilities

MCP support

The project implements an MCP server using the StepFun API, exposing text, vision, text-to-image, and speech model capabilities to MCP clients.

#stepfun#mcp#api-server

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "StepFunMCP": {
      "command": "uvx",
      "args": [
        "stepfun-mcp"
      ],
      "env": {
        "STEPFUN_API_KEY": "<STEPFUN_API_KEY>",
        "STEPFUN_API_HOST": "<STEPFUN_API_HOST>",
        "STEPFUN_MCP_BASE_PATH": "<STEPFUN_MCP_BASE_PATH>",
        "STEPFUN_API_RESOURCE_MODE": "<STEPFUN_API_RESOURCE_MODE>"
      }
    }
  }
}
Run commanduvx stepfun-mcp
Environment variables to set
STEPFUN_API_KEYSecret
STEPFUN_API_HOST
STEPFUN_MCP_BASE_PATH
STEPFUN_API_RESOURCE_MODE

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypistepfun-mcp

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

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 [email protected]:weidafeng/StepFunMCP.git
# pip install .
  1. 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"
      }
    }
  }
}

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.