Codeocean MCP Server

This MCP server provides tools to search and run capsules and pipelines, and manage data assets.

Local serverstdioPython

What is the Codeocean MCP server?

Codeocean becomes available to MCP clients through the codeocean mcp server. This MCP server provides tools to search and run capsules and pipelines, and manage data assets.

What Codeocean does

This MCP server provides tools to search and run capsules and pipelines, and manage data assets.

Tools it exposes

Once connected, the assistant can call these 2 tools directly:

  • macOS — ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows — %APPDATA%\Claude\claude_desktop_config.json

Installing the codeocean mcp server

The server is distributed via npm as @modelcontextprotocol/inspector, so most clients can run it without a manual build step. Add it to your MCP client's configuration and restart the client to pick it up — the copy-paste configs for Claude Desktop, Claude Code and Cursor are on this page.

Configuration

Before the server will start you need to supply 4 environment variables: CODEOCEAN_DOMAIN, CODEOCEAN_TOKEN, AGENT_ID, YOUR_API_KEY. Keep credentials in your client's env block or a secrets manager rather than committing them.

Requirements

  1. Install uv from Astral or the GitHub README 2. Install Python 3.10 or newer using uv python install 3.10 (or a more recent version) 3. Generate a Code Ocean access token. Follow instructions in the [Code Ocean user

Where it fits

Developer-tool servers are usually the first ones people connect, because they turn "help me with this code" into an assistant that can actually read the repo and act on it. Codeocean sits in that group, and the shape of its toolset — macOS, Windows — tells you what it is really for. Worth comparing against the other developer tools servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
  • It will not start until its required credentials are present, so set those before wondering why the tools never appear.
  • Maintained by codeocean, written in Python.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the codeocean mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
macOS~/Library/Application Support/Claude/claude_desktop_config.json
Windows%APPDATA%\Claude\claude_desktop_config.json

How to install the Codeocean MCP server

{
  "mcpServers": {
    "codeocean": {
      "command": "uvx",
      "args": ["codeocean-mcp-server"],
      "env": {
        "CODEOCEAN_DOMAIN": "https://codeocean.acme.com",
        "CODEOCEAN_TOKEN": "<YOUR_API_KEY>",
        "AGENT_ID": "Claude Desktop"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  1. Install uv from Astral or the GitHub README 2. Install Python 3.10 or newer using uv python install 3.10 (or a more recent version) 3. Generate a Code Ocean access token. Follow instructions in the [Code Ocean user
VariableDescriptionRequired
CODEOCEAN_DOMAINConfiguration value read at startup.Optional
CODEOCEAN_TOKENCredential the server authenticates with.Yes
AGENT_IDConfiguration value read at startup.Optional
YOUR_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Codeocean to macOS.
  • Use Codeocean to Windows.

Frequently asked questions

It connects Codeocean to MCP-compatible AI assistants such as Claude and Cursor, exposing 2 tools (macOS, Windows) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Codeocean directly.