MCP.so
登录

MCP Server Js

@yepcode

基本信息

分类

其他

许可证

MIT

传输方式

stdio

作者

yepcode

关于 MCP Server Js

MCP server that exposes YepCode processes as callable tools for AI platforms. Securely connect AI assistants to your YepCode workflows, APIs, and automations.

MCP Server Js 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "yepcode-mcp-server-stdio": {
      "command": "npx",
      "args": [
        "-y",
        "@yepcode/mcp-server"
      ],
      "env": {
        "YEPCODE_API_TOKEN": "your_api_token_here"
      }
    }
  },
  "yepcode-mcp-server-sse": {
    "url": "https://cloud.yepcode.io/mcp/sk-c2E....RD/sse"
  }
}

MCP Server Js 工具

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。

点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。

概览

What is Mcp Server Js?

Mcp Server Js is a Model Context Protocol server that enables AI platforms to interact with YepCode's infrastructure. It allows AI assistants to run LLM-generated scripts and turn YepCode processes into dynamic tools, defined with JSON Schema parameters and implemented in Python or Node.js.

How to use Mcp Server Js?

Requires Node.js 18+ or Docker and a YepCode API token. Configure your AI client (e.g., Cursor, Claude Desktop) with the command npx -y @yepcode/mcp-server and the YEPCODE_API_TOKEN environment variable. Alternatively, use Docker with docker run. The hosted MCP server at https://cloud.yepcode.io/mcp requires no local installation.

Key features of Mcp Server Js

  • Expose YepCode processes as MCP tools with JSON Schema parameters
  • Execute code securely in YepCode’s isolated environment via run_code
  • Manage environment variables, storage files, and processes
  • Polyglot tool implementations in Python or Node.js in one server
  • Control which tools are enabled via YEPCODE_MCP_TOOLS (tags and categories)
  • Enterprise-grade security with OAuth, API tokens, or workspace credentials

Use cases of Mcp Server Js

  • AI assistants executing LLM-generated code in a secure sandbox
  • Managing YepCode processes, schedules, variables, and storage through AI
  • Creating personalized AI tools by tagging custom processes as mcp-tool
  • Building a dynamic MCP tools server that mixes multiple programming languages

常见问题

1

What tools does Mcp Server Js provide?

Built-in tools include `run_code` for arbitrary code execution, `set_env_var` and `remove_env_var` for environment variables, and storage tools (`list_files`, `upload_file`, `download_file`, `delete_file`). Additionally, tagged YepCode processes become individual MCP tools.

2

How do I expose my own YepCode processes as MCP tools?

Tag your processes (e.g., `mcp-tool`, `core`) and set `YEPCODE_MCP_TOOLS` to a comma-separated list of those tags. Each tagged process will appear as a separate tool named by its slug.

3

What are the runtime requirements?

Node.js version 18 or higher (for NPX) or Docker. You must have a YepCode account and an API token stored in the `YEPCODE_API_TOKEN` environment variable.

4

Can I skip the run_code cleanup or coding rules?

Yes. Set the `YEPCODE_MCP_OPTIONS` environment variable to `runCodeCleanup` to keep source code after execution, or `skipCodingRules` to exclude included coding rules from the tool schema. Combine options as a comma-separated list.

5

How do I debug the MCP server?

Since MCP servers communicate over stdio, use the MCP Inspector by running `npm run inspector` locally. This provides a browser-based debugging interface.

评论

其他 分类下的更多 MCP 服务器