LibreChat Code Interpreter MCP Server

A Model Context Protocol (MCP) server that wraps the LibreChat Code Interpreter API, exposing code-execution and file-management endpoints as MCP tools. Easily integrate sandboxed code execution into any MCP-compatible client.

---

Features

• executeCode — Run arbitrary code (Python, JavaScript, TS, Go, C, C++, Java, PHP, Rust, Fortran, R, D, F90) in a secure sandbox
• downloadFile — Retrieve binary or text files generated during execution
• uploadFiles — Send files (binary or text) to a session for inclusion in code runs
• getFilesInfo — List metadata for files in a session (names, sizes, timestamps)
• deleteFile — Remove a file from a session

All operations require an API key from LibreChat Code Interpreter and adhere to MCP’s tools/list and tools/call schemas

---

Prerequisites

• Node.js ≥ 16
• npm or yarn
• A valid LibreChat API key (set in LIBRECHAT_API_KEY)

---

Installation

1# Clone this repo
2git clone <your-repo-url>
3cd <your-repo-folder>
4
5# Install dependencies
6yarn install   # or `npm install`

---

Configuration

Create a .env in the project root containing:

LIBRECHAT_API_KEY=sk-...your_api_key_here...

---

Running the Server

1# If using ts-node:
2npx ts-node src/librechat-mcp-server.ts
3
4# Or compile then run:
5tsc && node dist/librechat-mcp-server.js

By default, the server communicates over stdio (suitable for local MCP playgrounds, IPC, or Docker streams)

---

MCP Client Quick Start

Below is an example using the official MCP TypeScript SDK to call executeCode:

1import { Client } from "@modelcontextprotocol/sdk/client/index.js";
2import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";
3import { ListToolsResultSchema, CallToolResultSchema } from "@modelcontextprotocol/sdk/types";
4
5async function main() {
6  const transport = new StdioClientTransport({ command: "node dist/librechat-mcp-server.js" });
7  const client = new Client({ name: "example-client", version: "1.0.0" }, {});
8  await client.connect(transport);
9
10  // List available tools
11  const tools = await client.request(
12    { method: "tools/list" },
13    ListToolsResultSchema
14  );
15  console.log("Available MCP tools:", tools.tools.map(t => t.name));
16
17  // Execute Python code
18  const codeResult = await client.request(
19    {
20      method: "tools/call",
21      params: {
22        name: "executeCode",
23        arguments: {
24          code: "print(\"Hello from LibreChat!\")",
25          lang: "py",
26          user_id: "user123",
27          entity_id: "assistant_ABC123",
28          files: [],
29        },
30      },
31    },
32    CallToolResultSchema
33  );
34
35  console.log("Execution result:", codeResult.content[0].json);
36}
37
38main().catch(console.error);

---

Tool Schemas

Tool Name	Input Parameters
executeCode	code (string), lang (enum), args?, user_id?, entity_id?, files?
downloadFile	session_id (string), fileId (string)
uploadFiles	entity_id (string), files (array of { name, content, contentType })
getFilesInfo	session_id (string), detail? (simple or detailed)
deleteFile	session_id (string), fileId (string)

Combine these via MCP’s standard tools/list and tools/call messages to build powerful code-automation flows

---

Development

• Lint: npm run lint
• Type-check: npm run build
• Format: npm run format

Feel free to open issues or pull requests!