E2B MCP Server
Enables managing E2B cloud sandboxes, templates, filesystems, and processes through Model Context Protocol tools.
README
E2B MCP Server
An MCP server that exposes the E2B Sandbox API as Model Context Protocol tools.
Features
The server currently provides tools for:
- Sandboxes (
sandbox_create,sandbox_connect,sandbox_list,sandbox_kill,sandbox_pause,sandbox_set_timeout,sandbox_get_info) — create/connect/list/kill/pause sandboxes and manage their timeout, via the E2B JS SDK (Sandbox). - Filesystem (
files_read,files_write,files_list,files_make_dir,files_rename,files_remove,files_exists,files_get_info) — read/write/list/move/remove/stat files viaSandbox.files. - Commands (
commands_run,commands_connect,commands_list,commands_send_stdin,commands_close_stdin,commands_kill) — run and manage commands viaSandbox.commands. - PTY (
pty_create,pty_connect,pty_send_input,pty_resize,pty_kill) — pseudo-terminal sessions viaSandbox.pty.
The server is stateless: it authenticates with E2B_API_KEY (env) and, for secure sandboxes, replays the accessToken returned by sandbox_create / sandbox_connect on every later call.
Deprecated E2B API endpoints and snapshot-related functionality have been removed from the project.
Requirements
- Node.js 22 or later
- An E2B API key
Installation
npm ci
Configuration
Set your E2B API key in the environment:
export E2B_API_KEY="your-api-key"
Usage
Start the server with:
npm start
The server is designed to be used as an MCP server over stdio. It can be connected to any MCP-compatible client that supports stdio servers.
Docker
Build the image:
docker build -t e2b-mcp-server .
Run it:
docker run --rm -i \
-e E2B_API_KEY="$E2B_API_KEY" \
e2b-mcp-server
Development
Check the JavaScript syntax for all source files:
for f in src/*.js; do node --check "$f"; done
Run the smoke test:
npm run smoke
Project Structure
src/
├── http.js
├── index.js
├── tools-common.js
├── tools-filesystem.js
├── tools-process.js
├── tools-sandboxes.js
└── tools-templates.js
License
ISC
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.