socrata-mcp-server

Get Dataset Schema

socrata_get_dataset

Read-onlyIdempotent

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').

Input Schema

TableJSON Schema

Name	Required	Description	Default
`domain`	No	Portal the dataset lives on, as a bare hostname (e.g. data.cityofnewyork.us); URL forms like https://data.cityofnewyork.us/ are accepted and reduced to the host. Pass the domain from the same socrata_find_datasets result as dataset_id. Defaults to SOCRATA_DEFAULT_DOMAIN or data.seattle.gov, which is wrong for another portal’s ID.
`dataset_id`	Yes	Four-by-four dataset ID matching pattern like kzjm-xkqj. IDs are portal-scoped: take it from socrata_find_datasets together with that result’s domain.

Output Schema

TableJSON Schema

Name	Required	Description
`name`	No	Dataset display name.
`tags`	No	Associated tags.
`error`	No	Present when the call failed. Absent on success.
`domain`	No	Portal domain hosting this dataset.
`columns`	No	Column schema. Computed region columns (:@computed_region_*) are excluded to reduce noise.
`license`	No	License name when available.
`category`	No	Domain category when available.
`row_count`	No	Approximate row count when available. See row_count_source for provenance.
`dataset_id`	No	Four-by-four dataset ID.
`description`	No	Dataset description when available.
`data_updated_at`	No	ISO 8601 timestamp of last data update when available.
`row_count_source`	No	How row_count was obtained: 'top_level_cached_contents' — reported directly by the portal's views metadata; 'column_cached_contents' — derived as the maximum per-column cached count when the top-level value is absent. Absent when row_count is absent.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedSep 22, 2026

changedInput schema / properties / dataset_id / description

Previous value: -"Four-by-four dataset ID matching pattern like kzjm-xkqj. Obtain from socrata_find_datasets."New value: +"Four-by-four dataset ID matching pattern like kzjm-xkqj. IDs are portal-scoped: take it from socrata_find_datasets together with that result’s domain."

changedInput schema / properties / domain / description

Previous value: -"Portal domain (e.g. data.seattle.gov). Defaults to SOCRATA_DEFAULT_DOMAIN env var or data.seattle.gov."New value: +"Portal the dataset lives on, as a bare hostname (e.g. data.cityofnewyork.us); URL forms like https://data.cityofnewyork.us/ are accepted and reduced to the host. Pass the domain from the same socrata_find_datasets result as dataset_id. Defaults to SOCRATA_DEFAULT_DOMAIN or data.seattle.gov, which is wrong for another portal’s ID."

changedOutput schema / properties / error / properties / data / properties / reason / description

Previous value: -"Machine-readable failure mode. Declared by this tool: `invalid_id`: Dataset ID does not match the four-by-four pattern. `not_found`: Valid ID format but dataset does not exist on this domain. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_id`: Dataset ID does not match the four-by-four pattern. `not_found`: Valid ID format but the dataset does not exist on the domain queried — including a gateway HTTP 403 for an ID the portal does not serve. `unknown_domain`: The domain does not serve the Socrata API to this server: its hostname does not resolve (DNS ENOTFOUND), its API answered HTTP 404 without a Socrata error body, it redirected the request to another host that did not answer with Socrata data, or a gateway refused a dataset the Discovery catalog lists there. `invalid_domain`: The domain is not a hostname, even after dropping a URL scheme, path, or query. `rate_limited`: SODA endpoint returned 429. Other values are possible when a failure originates below the handler."

changedOutput schema / properties / error / properties / data / properties / reason / examples

Previous value: -[
-  "invalid_id",
-  "not_found"
-]New value: +[
+  "invalid_id",
+  "not_found",
+  "unknown_domain",
+  "invalid_domain",
+  "rate_limited"
+]

Changed6 schema fields changedAug 22, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

addedInput schema / additionalProperties
```
Added value: +false
```

changedOutput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

addedOutput schema / anyOf

Added value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "dataset_id",
+      "domain",
+      "name",
+      "tags",
+      "columns"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]

addedOutput schema / properties / error

Added value: +{
+  "additionalProperties": {},
+  "description": "Present when the call failed. Absent on success.",
+  "properties": {
+    "code": {
+      "description": "JSON-RPC error code for this failure.",
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "data": {
+      "additionalProperties": {},
+      "properties": {
+        "reason": {
+          "description": "Machine-readable failure mode. Declared by this tool: `invalid_id`: Dataset ID does not match the four-by-four pattern. `not_found`: Valid ID format but dataset does not exist on this domain. Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "invalid_id",
+            "not_found"
+          ],
+          "type": "string"
+        },
+        "recovery": {
+          "additionalProperties": {},
+          "description": "Actionable next step for the caller.",
+          "properties": {
+            "hint": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "hint"
+          ],
+          "type": "object"
+        },
+        "retryable": {
+          "description": "Whether retrying may succeed.",
+          "type": "boolean"
+        }
+      },
+      "type": "object"
+    },
+    "message": {
+      "description": "Human-readable description of what went wrong.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "code",
+    "message"
+  ],
+  "type": "object"
+}

removedOutput schema / required

Removed value: -[
-  "dataset_id",
-  "domain",
-  "name",
-  "tags",
-  "columns"
-]

Changed2 schema fields changedJul 5, 2026

changedOutput schema / properties / row_count / description

Previous value: -"Approximate row count when available."New value: +"Approximate row count when available. See row_count_source for provenance."

addedOutput schema / properties / row_count_source

Added value: +{
+  "description": "How row_count was obtained: 'top_level_cached_contents' — reported directly by the portal's views metadata; 'column_cached_contents' — derived as the maximum per-column cached count when the top-level value is absent. Absent when row_count is absent.",
+  "enum": [
+    "top_level_cached_contents",
+    "column_cached_contents"
+  ],
+  "type": "string"
+}

First observedMay 25, 2026

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and idempotentHint, so the description only needs to add context. It adds the return contents (field names, data types, descriptions, row count, licensing) and explains how the fetched column types inform downstream query syntax. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no filler: the first front-loads the operation and return list, the second delivers high-value usage guidance. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter tool with fully documented parameters, an output schema, and read-only/idempotent annotations, the description covers what the tool returns, when to call it, and why. Nothing essential is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with detailed descriptions for both domain and dataset_id. The description adds little parameter-specific meaning beyond the schema, so it meets the baseline without going further.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Fetch') and resource ('full metadata and column schema for a Socrata dataset by ID') and enumerates what it returns. It also differentiates itself from socrata_query_dataset by explicitly framing itself as the prerequisite for correct query construction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit workflow guidance: 'Always call this before writing a socrata_query_dataset' and explains why column types affect WHERE clause syntax. It does not, however, mention other sibling tools such as socrata_dataframe_describe or conditions where this tool should not be used.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All socrata-mcp-server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.