OpenGov MCP Server
Access Socrata Open Data APIs from government data portals.
OpenGov MCP Server
An MCP (Model Context Protocol) server that enables MCP clients like Claude Desktop to access Socrata Open Data APIs. This integration allows Claude Desktop to search for, retrieve, and analyze public datasets from government data portals.
Overview
This MCP server provides access to open data from any Socrata-powered data portal, including those from cities, states, and federal agencies such as:
No API key is required for basic usage, as the server accesses public data.
Features
With this MCP server, clients can:
- Search and discover datasets by keyword, category, or tags
- View dataset metadata and column information
- Run SQL-like queries to retrieve and analyze data
- Get portal usage statistics
Installation for Claude Desktop
Quick Setup with npx (Recommended)
The easiest way to use this MCP server is with npx, which doesn't require any installation:
-
Create or edit your Claude Desktop configuration:
Create or edit
claude_desktop_config.jsonin your home directory:{ "mcpServers": { "opengov": { "command": "npx", "args": ["-y", "opengov-mcp-server@latest"], "env": { "DATA_PORTAL_URL": "https://data.cityofchicago.org" } } } }You can replace the DATA_PORTAL_URL with any Socrata-powered data portal.
-
Restart Claude Desktop (if it was already running)
-
Start using the MCP server:
In Claude Desktop, you can now ask questions like:
How many cars were towed in Chicago this month?and you can follow up with questions that drill further into detail:
Which make and color were towed the most? Also, were there any interesting vanity plates?The first time you run a query, npx will automatically download and run the latest version of the server.
Manual Installation from Source
If you prefer to run from source (for development or customization):
-
Clone this repository:
git clone https://github.com/srobbin/opengov-mcp-server.git cd opengov-mcp-server -
Install dependencies and build:
npm install npm run build -
Create Claude Desktop configuration:
Create or edit
claude_desktop_config.jsonin your home directory:{ "mcpServers": { "opengov": { "command": "node", "args": [ "/path/to/your/opengov-mcp-server/dist/index.js" ], "env": { "DATA_PORTAL_URL": "https://data.cityofchicago.org" } } } }Replace
/path/to/your/opengov-mcp-serverwith the actual path where you cloned the repository. -
Restart Claude Desktop (if it was already running)
Available Tool: get_data
This MCP server provides a unified get_data tool that Claude Desktop uses to access Socrata data.
Parameters
-
type(string, required): Operation typecatalog: Search and list datasetscategories: List dataset categoriestags: List dataset tagsdataset-metadata: Get dataset detailscolumn-info: Get dataset column informationdata-access: Query and retrieve recordssite-metrics: Get portal statistics
-
domain(string, optional): Data portal hostname (without protocol) -
query(string, optional): Search query for datasets -
datasetId(string): Dataset identifier for specific operations -
soqlQuery(string, optional): SoQL query for filtering data -
limit(number, optional): Maximum results to return (default: 10) -
offset(number, optional): Results to skip for pagination (default: 0)
Example Queries
These are examples of how Claude Desktop will format queries to the MCP server:
// Find datasets about budgets
{
"type": "catalog",
"query": "budget",
"limit": 5
}
// Get information about a dataset
{
"type": "dataset-metadata",
"datasetId": "6zsd-86xi"
}
// Query dataset records with SQL-like syntax
{
"type": "data-access",
"datasetId": "6zsd-86xi",
"soqlQuery": "SELECT * WHERE amount > 1000 ORDER BY date DESC",
"limit": 10
}
Configuration Options
The server requires one environment variable:
DATA_PORTAL_URL: The Socrata data portal URL (e.g.,https://data.cityofchicago.org)
This can be set:
- In the Claude Desktop configuration (recommended)
- In your environment variables
- Via command line:
DATA_PORTAL_URL=https://data.cityofchicago.org opengov-mcp-server
संबंधित सर्वर
Redis
A server for interacting with Redis databases.
Graphiti MCP Server
A framework for building and querying temporally-aware knowledge graphs for AI agents.
Supabase
Interact with Supabase databases, query tables, and generate TypeScript types.
Tabular MCP Server
An MCP server for local Tabular Models like PowerBI. It allows LLM clients to debug, analyze, and compose DAX queries by connecting to a local Tabular model instance.
Iceberg MCP Server (via Impala)
Provides read-only access to Apache Iceberg tables via Apache Impala, allowing LLMs to inspect schemas and execute queries.
Multi Database MCP Server
An MCP server that provides AI assistants with structured access to multiple databases simultaneously.
MCP KQL Server
Execute KQL queries using Azure authentication. Requires Azure CLI login.
GraphRAG
Query a hybrid graph (Neo4j) and vector (Qdrant) database for powerful semantic and graph-based document retrieval.
Postgres MCP
Query any Postgres database using natural language.
engram-rs-mcp
MCP server for engram — persistent, brain-like memory for AI agents.