datagouv-mcp

Add the configuration to opencode.json (e.g., ~/.config/opencode/opencode.json or your project root). Remote servers must use the top-level mcp object with type: "remote".

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "datagouv": {
      "type": "remote",
      "url": "https://mcp.data.gouv.fr/mcp",
      "enabled": true
    }
  }
}

1. Open Cursor Settings.
2. Search for "MCP" or "Model Context Protocol".
3. Add a new MCP server with the following configuration:

{
  "mcpServers": {
    "datagouv": {
      "url": "https://mcp.data.gouv.fr/mcp",
      "transport": "http"
    }
  }
}

Available on all plans, including free.

1. Open Mistral in your browser and navigate to Intelligence > Connectors.
2. Click Add connector > Custom MCP Connector.
3. Provide a name (e.g., DataGouv) and set the server URL to https://mcp.data.gouv.fr/mcp.
4. Leave authentication disabled.
5. Click Create.

The recommended way to run the data.gouv.fr MCP server is using Docker Compose. This handles dependencies and environment setup automatically.

Setup

1. Clone the repository:

git clone git@github.com:datagouv/datagouv-mcp.git
cd datagouv-mcp

2. Ensure Docker Desktop or a compatible Docker Engine is installed.

Commands

• Start with default settings (Port 8000, production environment):

  docker compose up -d

- **Start with custom environment variables**:
  ```shell
MCP_PORT=8007 DATAGOUV_API_ENV=demo LOG_LEVEL=DEBUG docker compose up -d

• Stop the server:

  docker compose down

```shell
# With default settings (port 8000, prod environment)
docker compose up -d

# With custom environment variables
MCP_PORT=8007 DATAGOUV_API_ENV=demo LOG_LEVEL=DEBUG docker compose up -d

# Stop
docker compose down

Before submitting contributions, you must ensure your code follows the project's style guidelines. This project uses Ruff for linting and formatting (following PEP 8) and ty for type checking. You can run these checks manually using uv.

# Lint (including import sorting) and format code
uv run ruff check --fix && uv run ruff format

# Type check (ty)
uv run ty check

Add the configuration to your VS Code mcp.json file. You can open this file by running MCP: Open User Configuration from the Command Palette.

File Locations:

• Linux: ~/.config/Code/User/mcp.json
• MacOS: ~/Library/Application Support/Code/User/mcp.json
• Windows: %APPDATA%\Code\User\mcp.json

{
  "servers": {
    "datagouv": {
      "url": "https://mcp.data.gouv.fr/mcp",
      "type": "http"
    }
  }
}

Add the server configuration to your claude_desktop_config.json file.

File Locations:

• Linux: ~/.config/Claude/claude_desktop_config.json
• MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

Windows Troubleshooting: If the server appears but tools are missing, Claude may be using its built-in Node.js runtime which cannot see your system npm packages. To fix this, set isUsingBuiltInNodeForMcp to false at the root of your config file to force Claude to use your installed Node version.

{
  "isUsingBuiltInNodeForMcp": false,
  "mcpServers": {
    "datagouv": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://mcp.data.gouv.fr/mcp"
      ]
    }
  }
}

For both CLI and IDE, add the configuration to mcp.json.

File Locations:

• Workspace config: .kiro/settings/mcp.json
• Global config (Linux/MacOS): ~/.kiro/settings/mcp.json
• Global config (Windows): %USERPROFILE%\.kiro\settings\mcp.json

{
  "mcpServers": {
    "datagouv": {
      "url": "https://mcp.data.gouv.fr/mcp"
    }
  }
}

Note: Requires a paid plan (Plus, Pro, Team, or Enterprise).

1. Open ChatGPT in your browser and navigate to Settings > Apps and connectors.
2. Go to Advanced settings and enable Developer mode.
3. Return to Settings > Connectors > Browse connectors and click Add a new connector.
4. Set the URL to https://mcp.data.gouv.fr/mcp and save.

The project uses a tag_version.sh script to automate the release process, including creating git tags, generating GitHub releases, and updating CHANGELOG.md.

Prerequisites:

• GitHub CLI must be installed and authenticated.
• You must be on the main branch with a clean working directory.

Features:

• Automatically extracts commits since the last tag for the changelog.
• Identifies breaking changes (commits with !: in the subject).
• Creates and pushes the git tag.
• Creates a GitHub release.

# Create a new release
./tag_version.sh <version>

# Example
./tag_version.sh 2.5.0

# Dry run to see what would happen
./tag_version.sh 2.5.0 --dry-run

Locate the anythingllm_mcp_servers.json file in your AnythingLLM storage plugins directory:

• Linux: ~/.config/anythingllm-desktop/storage/plugins/anythingllm_mcp_servers.json
• MacOS: ~/Library/Application Support/anythingllm-desktop/storage/plugins/anythingllm_mcp_servers.json
• Windows: C:\Users\<username>\AppData\Roaming\anythingllm-desktop\storage\plugins\anythingllm_mcp_servers.json

Add the following configuration to the mcpServers object:

{
  "mcpServers": {
    "datagouv": {
      "type": "streamable",
      "url": "https://mcp.data.gouv.fr/mcp"
    }
  }
}