Giving Claude ability to run code with E2B via MCP (Model Context Protocol)
| Publisher | e2b-dev |
| Repository | mcp-server |
| Language | JavaScript |
| Forks | 68 |
| Stars | 394 |
| Available tools | 16 |
| Transport type | stdio |
| Categories | |
| License | Apache-2.0 |
| Links |
E2B Sandboxes exposes MCP capabilities that can be used by compatible AI clients and agents.
Browse the callable actions below, including names and descriptions when provided by the server.
Use the installation snippets to configure this server in your preferred MCP client.
394 stars and 68 forks from the linked repository.
Deprecated: This project is no longer actively maintained. It may not receive further updates or bug fixes.
This repository contains the source code for the E2B MCP server.
The E2B MCP server allows you to add code interpreting capabilities to your Claude Desktop app via the E2B Sandbox. See demo here.
Available in two editions:
You can also install E2B for Claude Desktop automatically via Smithery:
bashnpx @smithery/cli install e2b --client claude
Node.js 18+
{
"mcpServers": {
"e2b": {
"command": "npx",
"args": [
"-y",
"@e2b/mcp-server"
],
"env": {
"E2B_API_KEY": "<YOUR_API_KEY>"
}
}
}
}Create a new isolated sandbox environment for code execution with specified runtime (Python or JavaScript)
List all active sandboxes with their status, runtime type, and creation time
Delete a sandbox and clean up all associated resources and files
Execute Python or JavaScript code in a specified sandbox and return results
Upload a file to a sandbox's file system for use in code execution
Download a file from a sandbox's file system to retrieve execution results or outputs
List all files and directories in a sandbox's file system with metadata
Delete a specific file or directory from a sandbox's file system
Install a package (pip for Python, npm for JavaScript) in the specified sandbox environment
List all installed packages in a sandbox environment
Get detailed status information about a specific sandbox including resource usage
Retrieve execution logs and output history from a sandbox
Create a new file with specified content in a sandbox's file system
Read and return the contents of a file from a sandbox's file system
Update the contents of an existing file in a sandbox's file system
Get resource limits and quotas for a sandbox (CPU, memory, disk, execution time)
TypingMind connects MCP tools at the workspace level, so once E2B Sandboxes is connected, you can use it with different AI models in TypingMind instead of setting it up separately for each model. This MCP runs locally through the TypingMind MCP connector on your device.
Use this when the MCP server needs access to local files, apps, or private resources on your computer.
In TypingMind, go to Settings, Advanced Settings, then Model Context Protocol and choose Setup Connector.
Choose This Device, copy the command from TypingMind, and run it in Terminal. Keep the process running while you use MCP.
When the connector status is Ready, click Edit Servers and paste the MCP server configuration.
{
"mcpServers": {
"e2b-sandboxes": {
"command": "npx",
"args": [
"-y",
"@e2b/mcp-server"
]
}
}
}Save the server list, open Plugins, enable the E2B Sandboxes MCP tools, then select any supported AI model in TypingMind and use the tools in chat or assign them to an AI agent.
E2B Sandboxes is an MCP server that lets compatible AI clients connect to external tools and context. In TypingMind, you can add this MCP server once and make its tools available in your AI workspace.
Yes. TypingMind connects MCP tools at the workspace level, so you can use E2B Sandboxes with different AI models such as Claude, ChatGPT, Gemini, or other models you have configured in TypingMind without setting up the MCP server separately for each model.
TypingMind is one of the best frontends for LLM chat because it brings multiple AI models, prompts, plugins, AI agents, API keys, and MCP tools into one workspace. With E2B Sandboxes connected, you can use its MCP tools across your preferred models while keeping your chat workflow organized in TypingMind.
E2B Sandboxes runs through the TypingMind local MCP connector. This is best when the MCP server needs access to local files, desktop apps, command-line tools, or private resources on your computer.
E2B Sandboxes exposes 16 MCP tools that can be enabled from the TypingMind Plugins page and used in chat or assigned to AI agents.
No. TypingMind is local-first and lets you keep your model providers, API keys, prompts, and MCP configuration under your control. If E2B Sandboxes requires authentication, add the required headers, OAuth settings, or local configuration for that MCP server when you create the connection.
Deep Research MCP
Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.
Exa Search
Exa MCP for web search and web crawling!
Retool
Retool MCP server. Build internal tools, query databases, and deploy apps via Retool's low-code platform. Integrate with 100+ data sources from AI assistants.
Brave Search
UnknownIntegrate web search and local search capabilities with Brave. Brave Search allows you to seamlessly integrate Brave Search functionality into AI assistants like Claude. By implementing a Model Context Protocol (MCP) server, it enables the AI to leverage Brave Search's web search and local business search capabilities. It provides tools for both general web searches and specific local searches, enhancing the AI assistant's ability to provide relevant and up-to-date information.
Get notified about new features and future giveaways by subscribing to our newsletter 👇
