Code Ocean MCP Server

1

Add it to Claude Code

Run this in a terminal.

Run in terminal
claude mcp add -e "CODEOCEAN_DOMAIN=${CODEOCEAN_DOMAIN}" -e "CODEOCEAN_TOKEN=${CODEOCEAN_TOKEN}" codeocean -- uvx codeocean-mcp-server
Required:CODEOCEAN_DOMAINCODEOCEAN_TOKEN+ 1 optional
README.md

Search and execute Code Ocean capsules and pipelines while managing data assets.

Code Ocean MCP Server

Model Context Protocol (MCP) server for Code Ocean.

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

Prerequisites

  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 guide.

Code Ocean Platform Version Compatibility

Each release of this Code Ocean MCP Server is tested and verified against a specific minimum version of the Code Ocean platform API. Generally, this minimum version is the latest Code Ocean version at the time of the MCP Server release. We recommend ensuring your MCP Server dependency is pinned to a version compatible with your Code Ocean deployment. For details on when the minimum Code Ocean platform version changes, see the CHANGELOG.

Installation

[Visual Studio Code](https://code.visualstudio.com/docs/copilot/chat/mcp-servers)

Here's an example VS Code MCP server configuration:

{
    ...
    "mcp": {
        "inputs": [
            {
            "type": "promptString",
            "id": "codeocean-token",
            "description": "Code Ocean API Key", 
            "password": true
            }
        ],
        "servers": {
            "codeocean": {
                "type": "stdio",
                "command": "uvx",
                "args": ["codeocean-mcp-server"],
                "env": {
                    "CODEOCEAN_DOMAIN": "https://codeocean.acme.com",
                    "CODEOCEAN_TOKEN": "${input:codeocean-token}",
                    "AGENT_ID": "VS Code"
                }
            }
        },
    }
}

[Claude Desktop](https://modelcontextprotocol.io/quickstart/user)

  1. Open the claude_desktop_config.json file:
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  1. Under the top-level "mcpServers" object, add a "codeocean" entry. For a stdio transport (child-process) it looks like this:
{
  "mcpServers": {
    "codeocean": {
      "command": "uvx",
      "args": ["codeocean-mcp-server"],
      "env": {
        "CODEOCEAN_DOMAIN": "https://codeocean.acme.com",
        "CODEOCEAN_TOKEN": "<YOUR_API_KEY>",
        "AGENT_ID": "Claude Desktop"
      }
    }
  }
}

[Cline](https://docs.cline.bot/mcp/configuring-mcp-servers)

Cline stores all of its MCP settings in a JSON file called cline_mcp_settings.json. You can edit this either through the GUI (“Configure MCP Servers” in the MCP Servers pane) or by hand:

  1. Open Cline and click the MCP Servers icon in the sidebar.
  2. In the “Installed” tab, click Configure MCP Servers → this opens your cline_mcp_settings.json.
  3. Add a "codeocean" server under the "mcpServers" key. For stdio transport:
{
  "mcpServers": {
    "codeocean": {
      "command": "uvx",
      "args": ["codeocean-mcp-server"],
      "env": {
        "CODEOCEAN_DOMAIN": "https://codeocean.acme.com",
        "CODEOCEAN_TOKEN": "<YOUR_API_KEY>",
        "AGENT_ID": "Cline"
      },
      "alwaysAllow": [],       // optional: list of tools to auto-approve
      "disabled": false        // ensure it’s enabled
    }
  }
}
  1. Save the file. Cline will automatically detect and launch the new server, making your Code Ocean tools available in chat .

[Roo Code](https://docs.roocode.com/features/mcp/using-mcp-in-roo/)

Roo Code’s MCP support is configured globally across all workspaces via a JSON settings file or through its dedicated MCP Settings UI

Via the MCP Settings UI:
  1. Click the MCP icon in Roo Code’s sidebar. 
  2. Select Edit MCP Settings (opens cline_mcp_settings.json). 
  3. Under "mcpServers", add:
{
  "mcpServers": {
    "codeocean": {
      "command": "uvx",
      "args": ["codeocean-mcp-server"],
      "env": {
        "CODEOCEAN_DOMAIN": "https://codeocean.acme.com",
        "CODEOCEAN_TOKEN": "<YOUR_API_KEY>",
        "AGENT_ID": "Roo Code"
      }
    }
  }
}
  1. Save and restart Roo Code; your Code Ocean tools will appear automatically.
Optional: Manually editing cline_mcp_settings.json
  1. Locate cline_mcp_settings.json (in your home directory or workspace). 
  2. Insert the same "codeocean" block under "mcpServers" as above.
  3. Save and re

Tools (3)

search_capsulesSearch for Code Ocean capsules based on query parameters.
run_capsuleExecute a specific Code Ocean capsule.
manage_data_assetsList or retrieve information about platform data assets.

Environment Variables

CODEOCEAN_DOMAINrequiredThe URL of your Code Ocean deployment
CODEOCEAN_TOKENrequiredYour Code Ocean API access token
AGENT_IDIdentifier for the client application (e.g., Claude Desktop, Cline)

Configuration

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

Try it

Search for capsules related to genomic sequencing analysis.
Run the capsule with ID '12345-abcde' and report the status.
List all available data assets in my Code Ocean workspace.
Find and execute the latest pipeline for protein folding.

Frequently Asked Questions

What are the key features of Code Ocean?

Search and discover computational capsules and pipelines. Execute scientific workflows directly via natural language. Manage and retrieve platform data assets. Compatible with major IDEs like VS Code, Cursor, and Windsurf.

What can I use Code Ocean for?

Automating the execution of recurring scientific data processing pipelines. Quickly searching for existing research capsules to reuse in new projects. Managing large-scale research data assets directly from a coding environment. Integrating Code Ocean computational resources into AI-assisted research workflows.

How do I install Code Ocean?

Install Code Ocean by running: uvx codeocean-mcp-server

What MCP clients work with Code Ocean?

Code Ocean works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep Code Ocean docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare