\n\n[](https://github.com/cyanheads/socrata-mcp-server/releases/latest/download/socrata-mcp-server.mcpb) [](https://cursor.com/en/install-mcp?name=socrata-mcp-server&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBjeWFuaGVhZHMvc29jcmF0YS1tY3Atc2VydmVyIl19) [](https://vscode.dev/redirect?url=vscode:mcp/install?%7B%22name%22%3A%22socrata-mcp-server%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40cyanheads%2Fsocrata-mcp-server%22%5D%7D)\n\n[](https://www.npmjs.com/package/@cyanheads/mcp-ts-core)\n\n**Public Hosted Server:** [https://socrata.caseyjhand.com/mcp](https://socrata.caseyjhand.com/mcp)\n\n
\n\n---\n\n## Tools\n\nSix tools covering the full Socrata workflow — portal discovery, dataset search, schema inspection, SoQL querying, and DuckDB-powered analytical SQL over large result sets:\n\n| Tool | Description |\n|:---|:---|\n| `socrata_list_portals` | List known Socrata-powered government open-data portals with domain, organization name, and approximate dataset count |\n| `socrata_find_datasets` | Search for datasets across all Socrata portals or scope to one portal via the Discovery API |\n| `socrata_get_dataset` | Fetch full metadata and typed column schema for a dataset by ID — required before writing SoQL queries |\n| `socrata_query_dataset` | Execute a SoQL query against any dataset: search, select, where, group, having, order, with DataCanvas spillover |\n| `socrata_dataframe_describe` | List registered tables in a DataCanvas session — schema, row count, column names |\n| `socrata_dataframe_query` | Run SELECT-only SQL against DataCanvas tables populated by `socrata_query_dataset` |\n\n### `socrata_list_portals`\n\nList known Socrata-powered government open-data portals.\n\n- Curated catalog of 40 well-known city, county, state, and federal portals — every member verified live in the Discovery catalog\n- Per-portal dataset counts fetched live from the Discovery API, cached ~24 hours — approximate, point-in-time (`0` means the portal exposes no dataset assets to the catalog; `null` means the count is temporarily unavailable)\n- Client-side substring filtering on domain or organization name\n- Pagination (up to 200 per page) with offset\n- Returns domain (pass to `socrata_find_datasets`), organization name, and approximate dataset count\n- Use this first when you don't know which portal to target\n\n---\n\n### `socrata_find_datasets`\n\nSearch for datasets across all Socrata portals or scope to a single portal.\n\n- Full-text search across dataset names and descriptions\n- Scope to a single portal with the `domain` parameter\n- Filter by category (e.g. `[\"Public Safety\", \"Transportation\"]`) and tags (e.g. `[\"covid19\"]`)\n- Asset type filtering: datasets, maps, files, calendars, stories\n- Sort by relevance, page views, created date, or updated date\n- Pagination (up to 100 per page) with offset\n- Returns dataset IDs, names, abbreviated column previews, domains, and update timestamps\n- Column names here are preview-only — call `socrata_get_dataset` for typed schema before writing queries\n- Recovery hints on empty results — echoes applied filters and suggests how to broaden\n\n---\n\n### `socrata_get_dataset`\n\nFetch full metadata and column schema for a Socrata dataset by ID.\n\n- Returns field names, Socrata data types, descriptions, row count, and licensing\n- Column `data_type` determines correct WHERE clause syntax: `Number` → bare literals (`year=2023`), `Text` → single-quoted strings (`year='2023'`)\n- Excludes computed region columns (`:@computed_region_*`) to reduce noise\n- Per-column non-null row counts when available\n- Always call this before writing a `socrata_query_dataset` query\n\n---\n\n### `socrata_query_dataset`\n\nExecute a SoQL query against any dataset on any Socrata portal.\n\n- `search` parameter for quick full-text lookup across all text columns (`$q`)\n- `select`, `where`, `group`, `having`, `order` for full analytical control\n- SoQL operators: `=`, `!=`, `>`, `<`, `LIKE`, `IN(...)`, `BETWEEN`, `IS NULL`, `starts_with()`, `contains()`, `AND`, `OR`, `NOT`\n- Aggregation: `count(*)`, `sum()`, `avg()`, `min()`, `max()` with `group` and `having`\n- Pagination up to 5000 rows per call with offset; `total_count` returned when result is truncated\n- `assembled_query` in the response echoes the SoQL string for learning the syntax\n- All SODA 2.1 row values are strings — geo/location columns return nested objects\n- When `CANVAS_PROVIDER_TYPE=duckdb` and result hits the limit, rows spill to a DataCanvas table for SQL-based analysis\n\n---\n\n### `socrata_dataframe_describe`\n\nList registered tables in a DataCanvas session.\n\n- Shows table name, row count, and DuckDB-inferred column types for each registered table\n- Only meaningful when `CANVAS_PROVIDER_TYPE=duckdb` is set\n- Use after `socrata_query_dataset` spills a large result set\n- Returns canvas ID for use in `socrata_dataframe_query`\n\n---\n\n### `socrata_dataframe_query`\n\nRun SELECT-only SQL against DataCanvas tables populated by `socrata_query_dataset`.\n\n- DuckDB infers types from spilled data — numeric columns that SODA returned as strings become queryable with numeric comparisons (`year > 2020`, `amount < 500`)\n- SELECT-only enforcement: DDL, DML, and file-reading functions (`read_csv`, `read_parquet`) are rejected\n- Up to 10,000 rows per call\n- Works out of the box when `CANVAS_PROVIDER_TYPE=duckdb` is set — DuckDB ships as a regular dependency\n\n## Resources and prompts\n\n| Type | Name | Description |\n|:---|:---|:---|\n| Resource | `socrata://datasets/{domain}/{datasetId}` | Fetch full metadata and column schema for a dataset by stable URI — same payload as `socrata_get_dataset` |\n| Resource | `socrata://portals` | Paginated list of known Socrata portals with organization name and approximate dataset count |\n| Prompt | `explore_open_data` | Structured six-step civic data investigation workflow: find portal → discover datasets → inspect schema → query → aggregate → synthesize |\n\nAll resource data is also reachable via tools. Use the corresponding tool for agent workflows — resources are for clients that support URI-addressable data.\n\n## Features\n\nBuilt on [`@cyanheads/mcp-ts-core`](https://github.com/cyanheads/mcp-ts-core):\n\n- Declarative tool, resource, and prompt definitions — single file per primitive, framework handles registration and validation\n- Unified error handling — handlers throw, framework catches, classifies, and formats\n- Pluggable auth: `none`, `jwt`, `oauth`\n- Swappable storage backends: `in-memory`, `filesystem`, `Supabase`, `Cloudflare KV/R2/D1`\n- Structured logging with optional OpenTelemetry tracing\n- STDIO and Streamable HTTP transports\n- Optional DataCanvas (DuckDB, bundled) for analytical SQL over large result sets\n\nSocrata-specific:\n\n- Full Socrata SODA 2.1 API integration — SoQL query builder with select, where, group, having, order, search, limit, offset\n- Discovery API for cross-portal dataset search and per-portal dataset counts (curated 40-portal catalog, counts cached ~24h)\n- App token support (`SOCRATA_APP_TOKEN`) for higher per-IP rate limits\n- Configurable default portal domain via `SOCRATA_DEFAULT_DOMAIN`\n- Computed region column filtering to reduce noise in wide datasets\n- DataCanvas spillover — large query results automatically register as DuckDB tables for SQL analysis\n\nAgent-friendly output:\n\n- Assembled SoQL string echoed in every `socrata_query_dataset` response so agents can learn and refine syntax\n- Recovery hints on empty results — echoes applied filters with specific suggestions for broadening\n- Column type context embedded in schema output with WHERE-clause quoting rules stated explicitly\n- Per-item structured error reasons (`invalid_id`, `not_found`, `soql_error`, `rate_limited`) with actionable recovery text\n\n## Getting started\n\nAdd the following to your MCP client configuration file.\n\n```json\n{\n \"mcpServers\": {\n \"socrata-mcp-server\": {\n \"type\": \"stdio\",\n \"command\": \"bunx\",\n \"args\": [\"@cyanheads/socrata-mcp-server@latest\"],\n \"env\": {\n \"MCP_TRANSPORT_TYPE\": \"stdio\",\n \"MCP_LOG_LEVEL\": \"info\"\n }\n }\n }\n}\n```\n\nOr with npx (no Bun required):\n\n```json\n{\n \"mcpServers\": {\n \"socrata-mcp-server\": {\n \"type\": \"stdio\",\n \"command\": \"npx\",\n \"args\": [\"-y\", \"@cyanheads/socrata-mcp-server@latest\"],\n \"env\": {\n \"MCP_TRANSPORT_TYPE\": \"stdio\",\n \"MCP_LOG_LEVEL\": \"info\"\n }\n }\n }\n}\n```\n\nOr with Docker:\n\n```json\n{\n \"mcpServers\": {\n \"socrata-mcp-server\": {\n \"type\": \"stdio\",\n \"command\": \"docker\",\n \"args\": [\n \"run\", \"-i\", \"--rm\",\n \"-e\", \"MCP_TRANSPORT_TYPE=stdio\",\n \"ghcr.io/cyanheads/socrata-mcp-server:latest\"\n ]\n }\n }\n}\n```\n\nFor Streamable HTTP, set the transport and start the server:\n\n```sh\nMCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http\n# Server listens at http://localhost:3010/mcp\n```\n\n### Prerequisites\n\n- [Bun v1.3.0](https://bun.sh/) or higher (or Node.js v24+).\n- Optional: A Socrata app token — register for free at any portal (e.g. [data.seattle.gov](https://data.seattle.gov)) to get higher rate limits (10 req/s per token vs. shared throttled pool without one).\n\n### Installation\n\n1. **Clone the repository:**\n\n```sh\ngit clone https://github.com/cyanheads/socrata-mcp-server.git\n```\n\n2. **Navigate into the directory:**\n\n```sh\ncd socrata-mcp-server\n```\n\n3. **Install dependencies:**\n\n```sh\nbun install\n```\n\n4. **Configure environment:**\n\n```sh\ncp .env.example .env\n# edit .env and set SOCRATA_APP_TOKEN if you have one\n```\n\n## Configuration\n\nAll configuration is validated at startup via Zod schemas in `src/config/server-config.ts`. Key environment variables:\n\n| Variable | Description | Default |\n|:---|:---|:---|\n| `SOCRATA_APP_TOKEN` | Socrata app token (X-App-Token header). Without a token, requests share a throttled pool per source IP. | — |\n| `SOCRATA_DEFAULT_DOMAIN` | Default portal domain when `domain` is omitted from tool calls. | `data.seattle.gov` |\n| `MCP_TRANSPORT_TYPE` | Transport: `stdio` or `http`. | `stdio` |\n| `MCP_HTTP_PORT` | Port for HTTP server. | `3010` |\n| `MCP_SESSION_MODE` | Session handling: `stateful`, `stateless`, or `auto` (schema default `auto` resolves to stateful). This server sets it explicitly to stateless. | `stateless` |\n| `MCP_AUTH_MODE` | Auth mode: `none`, `jwt`, or `oauth`. | `none` |\n| `MCP_LOG_LEVEL` | Log level (RFC 5424): `debug`, `info`, `notice`, `warning`, `error`. | `info` |\n| `CANVAS_PROVIDER_TYPE` | Set to `duckdb` to enable DataCanvas spillover for large result sets. DuckDB ships with the server — no additional install required. | — |\n| `LOGS_DIR` | Directory for log files (Node.js only). | `/logs` |\n| `STORAGE_PROVIDER_TYPE` | Storage backend: `in-memory`, `filesystem`, `supabase`, `cloudflare-kv/r2/d1`. | `in-memory` |\n| `OTEL_ENABLED` | Enable [OpenTelemetry instrumentation](https://github.com/cyanheads/mcp-ts-core/tree/main/docs/telemetry). | `false` |\n\nSee [`.env.example`](./.env.example) for the full list of optional overrides.\n\n## Running the server\n\n### Local development\n\n- **Build and run:**\n\n ```sh\n # One-time build\n bun run rebuild\n\n # Run the built server\n bun run start:stdio\n # or\n bun run start:http\n ```\n\n- **Run checks and tests:**\n\n ```sh\n bun run devcheck # Lint, format, typecheck, security audit\n bun run test # Vitest test suite\n ```\n\n### Docker\n\n```sh\ndocker build -t socrata-mcp-server .\ndocker run --rm -e MCP_TRANSPORT_TYPE=http -p 3010:3010 socrata-mcp-server\n```\n\nThe Dockerfile defaults to HTTP transport, stateless session mode, and logs to `/var/log/socrata-mcp-server`. OpenTelemetry peer dependencies are installed by default — build with `--build-arg OTEL_ENABLED=false` to omit them.\n\n## Project structure\n\n| Directory | Purpose |\n|:---|:---|\n| `src/index.ts` | `createApp()` entry point — registers tools, resources, prompts, and inits the Socrata service. |\n| `src/config` | Server-specific environment variable parsing and validation with Zod. |\n| `src/mcp-server/tools` | Tool definitions (`*.tool.ts`). Six tools covering portal listing, dataset search, schema fetch, SoQL query, and DataCanvas SQL. |\n| `src/mcp-server/resources` | Resource definitions (`*.resource.ts`). Dataset metadata and portal catalog resources. |\n| `src/mcp-server/prompts` | Prompt definitions (`*.prompt.ts`). Civic data investigation workflow prompt. |\n| `src/services/socrata` | Socrata service layer — SODA 2.1 API client, Discovery API, query builder, type normalization. |\n| `tests/` | Unit and integration tests mirroring `src/`. |\n\n## Development guide\n\nSee [`CLAUDE.md`](./CLAUDE.md) for development guidelines and architectural rules. The short version:\n\n- Handlers throw, framework catches — no `try/catch` in tool logic\n- Use `ctx.log` for request-scoped logging, `ctx.state` for tenant-scoped storage\n- Call `socrata_get_dataset` before writing WHERE clauses — column `data_type` determines quoting\n- Wrap external API calls: validate raw → normalize to domain type → return output schema; never fabricate missing fields\n\n## License\n\nApache-2.0 — see [LICENSE](LICENSE) for details.\n",
"bytes": 14764,
"sha": "6df1003dbfedc8504a27ebd2953e8691cc3b76e280170fab3ef735925357a4dc",
"repo_slug": "cyanheads/socrata-mcp-server",
"fonte": "repo",
"truncated": false,
"api": "https://agentalog.com/api/listings/mcp_io_github_cyanheads_socrata_mcp_server_8295e6a5/readme"
}