Search and query government open-data portals (Socrata SODA API) via MCP. STDIO or Streamable HTTP.
claude mcp add --transport http socrata-mcp-server https://socrata.caseyjhand.com/mcpcodex mcp add socrata-mcp-server --url https://socrata.caseyjhand.com/mcp{
"mcpServers": {
"socrata-mcp-server": {
"url": "https://socrata.caseyjhand.com/mcp"
}
}
}gemini mcp add --transport http socrata-mcp-server https://socrata.caseyjhand.com/mcp{
"mcpServers": {
"socrata-mcp-server": {
"command": "bunx",
"args": [
"mcp-remote",
"https://socrata.caseyjhand.com/mcp"
]
}
}
}{
"mcpServers": {
"socrata-mcp-server": {
"type": "http",
"url": "https://socrata.caseyjhand.com/mcp"
}
}
}curl -X POST https://socrata.caseyjhand.com/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-11-25","capabilities":{},"clientInfo":{"name":"curl","version":"1.0.0"}}}'Search for datasets across all Socrata-powered government open-data portals, or scope to one portal with the domain parameter. Returns dataset IDs, names, domains, update timestamps, and column_names — the API field names SoQL takes, not display labels. Use socrata_get_dataset to fetch the typed column schema before writing queries — column_names carry no type information.
Fetch full metadata and column schema for a Socrata dataset by ID. Returns field names, data types, descriptions, row count, and licensing. Always call this before writing a socrata_query_dataset — the column types determine correct WHERE clause syntax: Number columns accept bare literals (year=2023) while Text columns require single-quoted strings (year='2023').
Execute a SoQL query against any dataset on any Socrata portal. Use the search parameter for quick full-text lookup, or combine select/where/group/having/order for full analytical control. Returns rows plus the assembled SoQL string so you can learn the pattern. Columns are referenced by API field name (field_name from socrata_get_dataset, e.g. cuisine_description), never the display label. All SODA 2.1 row values are strings even for numeric columns — check data_type from socrata_get_dataset to determine correct WHERE quoting: Number columns use bare literals (year=2023), Text columns use single-quoted strings (year='2023'). To enumerate distinct values, use select="col, count(*) as n" with group="col" and order="n DESC". When CANVAS_PROVIDER_TYPE=duckdb and rows fill limit, up to 50,000 matching rows spill to a DataCanvas table whatever the limit: list its columns with socrata_dataframe_describe, then run SQL with socrata_dataframe_query.
List known Socrata-powered government open-data portals with their domain, organization name, and approximate dataset count. The catalog is a curated list of 39 well-known portals; dataset counts are fetched from the Discovery API and cached for ~24 hours. Filtering is client-side substring match on the query parameter. Use this first when you do not know which portal to target, then pass the domain to socrata_find_datasets.
List registered tables in a DataCanvas session — schema, row count, and column names. Shows what datasets are available for SQL queries via socrata_dataframe_query. Only meaningful when CANVAS_PROVIDER_TYPE=duckdb is set. Use after socrata_query_dataset spills a large result set to canvas.
Run SELECT-only SQL against a DataCanvas table populated by socrata_query_dataset. Columns SODA types as number (including aggregate aliases like count(*) as n) are staged as DOUBLE, so numeric comparisons work without a cast (year > 2020, amount < 500). Text and timestamp columns stay VARCHAR — compare times with CAST(date AS TIMESTAMP). Only works when CANVAS_PROVIDER_TYPE=duckdb is set. Use socrata_dataframe_describe to see registered tables and their schemas.
Permanently remove staged DataCanvas data — the whole canvas, or one table on it when table_name is given. Dropping the canvas invalidates its canvas_id: socrata_dataframe_describe and socrata_dataframe_query calls with it then fail as canvas_not_found. Dropping one table leaves the canvas and its other tables in place. Only the server's staged copy is deleted; the portal data is untouched, and socrata_query_dataset can stage it again. Call socrata_dataframe_describe first to see what a canvas holds. Only works when CANVAS_PROVIDER_TYPE=duckdb is set.
No tools match the current filter.
Fetch full metadata and column schema for a Socrata dataset addressable by stable URI. Same payload as socrata_get_dataset. Name, description, and column descriptions are upstream-provided portal metadata, not server-authored text. URI format: socrata://datasets/{domain}/{datasetId} (e.g. socrata://datasets/data.seattle.gov/kzjm-xkqj).
List of known Socrata-powered government open-data portals with organization name and approximate dataset count. The catalog is a curated list of 39 well-known portals; dataset counts are fetched from the Discovery API and cached for ~24 hours (null when temporarily unavailable). Paginated — default 50 per page. Use the domain values with socrata_find_datasets to search a specific portal.
Structured workflow for investigating a civic data question. Guides: discover relevant datasets on the right portal, inspect schemas, query for baseline data, group/aggregate for trends, and synthesize findings with data-freshness caveats.
topicrequired
— Civic data topic or question to investigate (e.g. "traffic collisions in 2023", "food inspection failures", "311 service requests by neighborhood").
portal
— Target portal domain if known (e.g. data.seattle.gov). Omit to use socrata_list_portals to find the right portal first.
geography
— Geographic scope to focus on (e.g. "Seattle", "King County", "New York City"). Used to scope WHERE clauses.