YepCode MCP Server

The YepCode MCP Server is an MCP (Model Context Protocol) server that enables AI platforms to interact with YepCode’s infrastructure. Run LLM-generated scripts and turn your YepCode processes into powerful tools that AI assistants can use directly.

YepCode is the perfect environment to build a dynamic MCP tools server: expose each process as a tool, define each tool’s parameters with JSON Schema for full flexibility, and implement tools in Python or Node.js — all in one server that mixes multiple languages.

• Seamless AI Integration — Convert YepCode processes into AI-ready tools with zero configuration.
• Real-time Process Control — Enable direct interaction between AI systems and your workflows.
• Enterprise-Grade Security — Execute code in YepCode’s isolated, production-ready environments.
• Universal Compatibility — Integrate with any AI platform supporting the Model Context Protocol, such as Cursor or Claude Desktop.

YepCode is built to be the ideal platform for running a dynamic MCP tools server:

Each YepCode process can be exposed as an MCP tool. Tag your processes (e.g. mcp-tool, core, automation) and they become tool sets that AI assistants can invoke. You can secure access with OAuth or YepCode API tokens, and services can be accessed using your defined credentials.

Every tool can define its own parameter schema as JSON Schema. You get complete flexibility to describe inputs (types, descriptions, required fields, enums, defaults, etc.), so the AI receives rich metadata and can call your tools correctly.

Implement tools in Python or Node.js (or both). The same MCP server can expose tools backed by different runtimes — think of it as one MCP server that mixes implementations across several languages.

The MCP server provides several built-in tools to interact with YepCode’s infrastructure.

Execute code directly in YepCode’s secure environment. Supports both JavaScript and Python.

// Input
{
  code: string;
  options?: {
    language?: string;      // 'javascript' (default) or 'python'
    comment?: string;
    settings?: Record<string, unknown>;
  }
}

// Response
{
  returnValue?: unknown;
  logs?: string[];
  error?: string;
}

Expose your YepCode Processes as individual MCP tools, making them directly accessible to AI assistants:

1. Tag your YepCode processes with any tag (e.g. core, api, automation, mcp-tool)
2. Add those tags to the YEPCODE_MCP_TOOLS configuration
3. All matching processes become individual MCP tools, named using the process slug

Each process tool accepts parameters matching the process’s input schema and can run either synchronously (waiting for the result) or asynchronously (returning an execution ID immediately).

For more information about process tags, see the process tags documentation.

YepCode provides a built-in storage system accessible from your code executions via yepcode.storage. The MCP server provides the following tools to manage storage:

• list_files — List all files, optionally filtered by prefix.
• upload_file — Upload text or binary (base64) content.
• download_file — Download a file.
• delete_file — Delete a file.

Our REST API may be used from the MCP server to manage your YepCode workspace. There are two levels of API management tools available:

For more information about the MCP server, please refer to the MCP server documentation.