Data.gov MCP Server
# Data.gov MCP Server
An MCP server for accessing data from Data.gov, providing tools and resources for interacting with government datasets.
<a href="https://glama.ai/mcp/servers/qi5i2d6sen">
<img width="380" height="200" src="https://glama.ai/mcp/servers/qi5i2d6sen/badge" alt="Data.gov Server MCP server" />
</a>
## Installation
1. **Install the package globally:**
```bash
npm install -g @melaodoidao/datagov-mcp-server
```
2. **Configure the MCP Server:**
- Add the following entry to your `cline_mcp_settings.json` file (usually located in `~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/` on macOS):
```json
{
"mcpServers": {
"datagov": {
"command": "datagov-mcp-server",
"args": [],
"env": {}
}
}
}
```
- If you are using the Claude Desktop app, add the entry to `~/Library/Application Support/Claude/claude_desktop_config.json` instead.
## Usage
This server provides the following tools:
* `package_search`: Search for packages (datasets) on Data.gov.
* `package_show`: Get details for a specific package (dataset).
* `group_list`: List groups on Data.gov.
* `tag_list`: List tags on Data.gov.
It also provides the following resource template:
* `datagov://resource/{url}`: Access a Data.gov resource by its URL.
You can use these tools and resources with Cline by specifying the server name (`datagov-mcp-server`) and the tool/resource name.
## Contributing
Contributions are welcome! Please feel free to submit issues or pull requests.
## License
MIT LicenseTDQS
Scored across 4 tools
Each tool has a clearly distinct purpose targeting different resources: groups, packages (datasets), and tags. The actions (list, search, show) are well-defined and non-overlapping, making it easy for an agent to select the right tool without confusion.
All tool names follow a consistent snake_case pattern with a clear verb_noun structure (e.g., group_list, package_search). This predictability enhances readability and usability across the tool set.
With only 4 tools, the set feels thin for a data portal server, lacking operations like create, update, or delete for resources. While the tools cover basic read/search functions, the scope could be expanded for more comprehensive coverage.
The tool surface is severely incomplete for a data management domain, missing essential CRUD operations (e.g., no create_package, update_package, delete_package) and other common actions like resource_show for groups or tags. This will likely cause agent failures when trying to perform full lifecycle tasks.