Skip to main content
Glama

usgs-water-mcp-server

by io.github.cyanheads
OverviewDiscussionsAdmin

Water Dataframe Query

water_dataframe_query
Read-onlyIdempotent

Run a read-only SQL SELECT against water data tables staged on a DataCanvas by water_get_series or water_find_sites. Workflow: run water_get_series or water_find_sites (get canvas_id + table_name) → water_dataframe_describe (confirm the table and its columns) → water_dataframe_query (SQL analysis). Only SELECT statements are permitted. At most 10,000 rows are returned; a query matching more is capped and the response sets truncated=true — scope with WHERE/LIMIT, and use SELECT COUNT(*) or water_dataframe_describe to learn the true match count. Requires DataCanvas to be enabled on this server instance. Returns an error if DataCanvas is not available.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sqlYesRead-only SELECT statement. Reference the table by the table_name from water_get_series or water_find_sites; columns vary by source table, so run water_dataframe_describe first for the exact schema. Example: SELECT date_time, value FROM water_series_01646500_00060 ORDER BY date_time DESC LIMIT 10
canvas_idYesCanvas ID returned by water_get_series or water_find_sites. Identifies the canvas holding the data.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
rowsNoResult rows returned (up to 10,000). Column names match the SELECT clause.
errorNoPresent when the call failed. Absent on success.
row_countNoNumber of rows returned in the rows array (up to the 10,000-row cap), not the total matched by the query. When truncated is true the cap was reached, so row_count equals the returned count and undercounts the true total. To get the true match count run SELECT COUNT(*) with the same filter, or call water_dataframe_describe for the full row count of the staged table; page large results with LIMIT/OFFSET.
truncatedNoTrue when the query matched more rows than the 10,000-row cap and the result was capped — rows and row_count then cover only the first 10,000 matches, and the rest are not in this response. False means rows and row_count are the complete result for this query. When true, narrow the query with WHERE, page with LIMIT/OFFSET, or run SELECT COUNT(*) with the same filter for the true total.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / canvas_id / pattern
      Added value: +"^[A-Za-z0-9_-]{10}$"
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `canvas_disabled`: DataCanvas is not enabled on this server instance. `canvas_not_found`: The canvas_id does not exist or has expired. `table_not_found`: The SQL names a table that is not staged on this canvas — it may have expired, or was never created. `system_catalog_access`: The SQL reads a database system catalog (information_schema, pg_catalog, sqlite_master, duckdb_*) instead of a staged table. `invalid_sql`: The SQL is not a read-only SELECT, contains disallowed functions, or is syntactically invalid. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `canvas_disabled`: DataCanvas is not enabled on this server instance. `canvas_not_found`: The canvas_id does not exist or has expired. `table_not_found`: The SQL names a table that is not staged on this canvas — it may have expired, or was never created. `system_catalog_access`: The SQL reads a database system catalog (information_schema, pg_catalog, sqlite_master, duckdb_*) instead of a staged table. `invalid_sql`: The SQL is not a read-only SELECT, contains disallowed functions, is syntactically invalid, or failed on the staged data (a cast or conversion the engine could not apply). Other values are possible when a failure originates below the handler."
  2. Changed6 schema fields changed
    • 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": [
+      "rows",
+      "row_count",
+      "truncated"
+    ]
+  },
+  {
+    "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: `canvas_disabled`: DataCanvas is not enabled on this server instance. `canvas_not_found`: The canvas_id does not exist or has expired. `table_not_found`: The SQL names a table that is not staged on this canvas — it may have expired, or was never created. `system_catalog_access`: The SQL reads a database system catalog (information_schema, pg_catalog, sqlite_master, duckdb_*) instead of a staged table. `invalid_sql`: The SQL is not a read-only SELECT, contains disallowed functions, or is syntactically invalid. Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "canvas_disabled",
+            "canvas_not_found",
+            "table_not_found",
+            "system_catalog_access",
+            "invalid_sql"
+          ],
+          "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: -[
-  "rows",
-  "row_count",
-  "truncated"
-]
  3. Changed3 schema fields changed
    • changedOutput schema / properties / row_count / description
      Previous value: -"Number of rows returned in the rows array (up to the 10,000-row cap), not the total matched by the query. A query matching more than 10,000 rows is truncated silently, so row_count then equals the returned count and undercounts the true total. To get the true match count run SELECT COUNT(*) with the same filter, or call water_dataframe_describe for the full row count of the staged table; page large results with LIMIT/OFFSET."New value: +"Number of rows returned in the rows array (up to the 10,000-row cap), not the total matched by the query. When truncated is true the cap was reached, so row_count equals the returned count and undercounts the true total. To get the true match count run SELECT COUNT(*) with the same filter, or call water_dataframe_describe for the full row count of the staged table; page large results with LIMIT/OFFSET."
    • addedOutput schema / properties / truncated
      Added value: +{
+  "description": "True when the query matched more rows than the 10,000-row cap and the result was capped — rows and row_count then cover only the first 10,000 matches, and the rest are not in this response. False means rows and row_count are the complete result for this query. When true, narrow the query with WHERE, page with LIMIT/OFFSET, or run SELECT COUNT(*) with the same filter for the true total.",
+  "type": "boolean"
+}
    • changedOutput schema / required
      Previous value: -[
-  "rows",
-  "row_count"
-]New value: +[
+  "rows",
+  "row_count",
+  "truncated"
+]
  4. Changed3 schema fields changed
    • changedInput schema / properties / canvas_id / description
      Previous value: -"Canvas ID returned by water_get_series. Identifies the canvas holding the data."New value: +"Canvas ID returned by water_get_series or water_find_sites. Identifies the canvas holding the data."
    • changedInput schema / properties / sql / description
      Previous value: -"Read-only SELECT statement. Reference tables by the names returned in water_get_series table_name. Columns available: date_time (VARCHAR), value (VARCHAR), qualifiers (VARCHAR), site_number (VARCHAR), parameter_cd (VARCHAR), unit_code (VARCHAR). Example: SELECT date_time, value FROM water_series_01646500_00060 ORDER BY date_time DESC LIMIT 10"New value: +"Read-only SELECT statement. Reference the table by the table_name from water_get_series or water_find_sites; columns vary by source table, so run water_dataframe_describe first for the exact schema. Example: SELECT date_time, value FROM water_series_01646500_00060 ORDER BY date_time DESC LIMIT 10"
    • changedOutput schema / properties / row_count / description
      Previous value: -"Total rows matched by the query before the 10,000-row cap. When row_count > rows.length, add WHERE or LIMIT clauses to retrieve specific subsets."New value: +"Number of rows returned in the rows array (up to the 10,000-row cap), not the total matched by the query. A query matching more than 10,000 rows is truncated silently, so row_count then equals the returned count and undercounts the true total. To get the true match count run SELECT COUNT(*) with the same filter, or call water_dataframe_describe for the full row count of the staged table; page large results with LIMIT/OFFSET."
  5. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the readOnlyHint and idempotentHint annotations, the description discloses a 10,000-row cap, the truncated=true response behavior, the SELECT-only restriction, and the DataCanvas availability requirement. This gives an agent actionable expectations about side effects and limits.

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?

The description is front-loaded with the core purpose, followed by a compact workflow, constraints, and boundary conditions. Every sentence contributes useful information with no filler or repetition.

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?

With a full input schema and an output schema present, the description covers all needed context: prerequisites, workflow ordering, SQL restrictions, row-cap behavior, and failure mode when DataCanvas is unavailable. An agent has enough information to invoke this tool correctly.

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?

Input schema coverage is 100% and both parameters already have detailed descriptions, including an example SQL statement. The tool description adds workflow context but does not materially enrich the meaning of the parameters themselves, so the baseline score of 3 is appropriate.

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?

The description states a precise action: run a read-only SQL SELECT against water data tables staged on a DataCanvas by water_get_series or water_find_sites. This clearly distinguishes the tool from data-fetching siblings and positions it as the analysis step in the workflow.

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

Usage Guidelines5/5

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

The description gives an explicit workflow: call water_get_series or water_find_sites first, then water_dataframe_describe to confirm schema, then water_dataframe_query for SQL analysis. It also tells when to use SELECT COUNT(*) or water_dataframe_describe instead, making alternatives and exclusions clear.

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

All usgs-water-mcp-server toolsInspect
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.

Resources