Skip to main content
Glama

open-meteo-mcp-server

by io.github.cyanheads
OverviewDiscussionsAdmin

Openmeteo Dataframe Query

openmeteo_dataframe_query
Read-only

Run a read-only SQL SELECT against tables staged on a DataCanvas by openmeteo_get_forecast, openmeteo_get_historical, openmeteo_get_marine, openmeteo_get_air_quality, openmeteo_get_ensemble, openmeteo_get_flood, or openmeteo_get_climate. Pass the canvas_id returned when any of those tools spills (truncated: true), and reference the exact table_name those tools return alongside it. Call openmeteo_dataframe_describe to list staged tables and their columns when you need to discover names. Returns up to 100 leading rows — fewer when wide rows would pass the 80,000-character inline ceiling — plus row_count — exact, or a lower bound flagged by count_error when counting fails or runs past 5 seconds; page the rest with LIMIT / OFFSET.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sqlYesRead-only SELECT statement. Reference table names from openmeteo_dataframe_describe. Example: SELECT AVG(temperature_2m) AS avg_temp, strftime(time, '%Y-%m') AS month FROM spilled_abc123 GROUP BY month ORDER BY month
canvas_idYesCanvas ID returned by openmeteo_get_forecast, openmeteo_get_historical, openmeteo_get_marine, openmeteo_get_air_quality, openmeteo_get_ensemble, openmeteo_get_flood, or openmeteo_get_climate when truncated: true.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
rowsNoLeading result rows: at most 100, and fewer when the next row would take the response past its 80,000-character inline ceiling. Values are never cut. When row_count exceeds rows.length, continue by re-issuing the SQL with OFFSET <rows.length>, added to any OFFSET it already applies, with any LIMIT reduced by the same amount. Page under an ORDER BY: without one, DuckDB guarantees no row order between calls.
errorNoPresent when the call failed. Absent on success.
canvas_idNoCanvas ID that was queried.
row_countNoExact number of rows in the full result. When count_error is present, the total could not be counted and this is a lower bound: the rows the query confirmed exist.
count_errorNoPresent only when counting the full result failed after its rows were read — the failure reason (e.g. sql_execution_error, or count_timeout when counting ran past 5 seconds). The rows are still valid; row_count is then a lower bound.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedOutput schema / properties / count_error
      Added value: +{
+  "description": "Present only when counting the full result failed after its rows were read — the failure reason (e.g. sql_execution_error, or count_timeout when counting ran past 5 seconds). The rows are still valid; row_count is then a lower bound.",
+  "type": "string"
+}
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `canvas_not_enabled`: CANVAS_PROVIDER_TYPE is not set to duckdb. `canvas_not_found`: The canvas_id is unknown or has expired under its 24 h sliding TTL. `system_catalog_access`: The SQL references a system catalog such as information_schema, sqlite_master, pg_catalog, or a duckdb_*() function. `missing_table`: The SQL references a table that is not staged on this canvas — a mistyped name, or one that expired (24 h sliding TTL) or was dropped. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `canvas_not_enabled`: CANVAS_PROVIDER_TYPE is not set to duckdb. `canvas_not_found`: The canvas_id is unknown or has expired under its 24 h sliding TTL. `system_catalog_access`: The SQL references a system catalog such as information_schema, sqlite_master, pg_catalog, or a duckdb_*() function. `missing_table`: The SQL references a table that is not staged on this canvas — a mistyped name, or one that expired (24 h sliding TTL) or was dropped. `row_too_large`: The first result row alone cannot fit the 80,000-character inline ceiling, and values are never cut. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / error / properties / data / properties / reason / examples
      Previous value: -[
-  "canvas_not_enabled",
-  "canvas_not_found",
-  "system_catalog_access",
-  "missing_table"
-]New value: +[
+  "canvas_not_enabled",
+  "canvas_not_found",
+  "system_catalog_access",
+  "missing_table",
+  "row_too_large"
+]
    • changedOutput schema / properties / row_count / description
      Previous value: -"Total rows in the full result before any cap."New value: +"Exact number of rows in the full result. When count_error is present, the total could not be counted and this is a lower bound: the rows the query confirmed exist."
    • changedOutput schema / properties / rows / description
      Previous value: -"Result rows — a preview capped at 100. When row_count exceeds this, page the rest by re-issuing the SQL with LIMIT / OFFSET."New value: +"Leading result rows: at most 100, and fewer when the next row would take the response past its 80,000-character inline ceiling. Values are never cut. When row_count exceeds rows.length, continue by re-issuing the SQL with OFFSET <rows.length>, added to any OFFSET it already applies, with any LIMIT reduced by the same amount. Page under an ORDER BY: without one, DuckDB guarantees no row order between calls."
  2. Changed1 schema field changed
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `canvas_not_enabled`: CANVAS_PROVIDER_TYPE is not set to duckdb. `canvas_not_found`: The canvas_id is unknown or has expired (TTL is 24 h sliding). `system_catalog_access`: The SQL references a system catalog (information_schema, sqlite_master, pg_catalog, or a duckdb_*() function). `missing_table`: The SQL references a table that is not staged on this canvas — a mistyped name, or one that expired (24 h sliding TTL) or was dropped. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `canvas_not_enabled`: CANVAS_PROVIDER_TYPE is not set to duckdb. `canvas_not_found`: The canvas_id is unknown or has expired under its 24 h sliding TTL. `system_catalog_access`: The SQL references a system catalog such as information_schema, sqlite_master, pg_catalog, or a duckdb_*() function. `missing_table`: The SQL references a table that is not staged on this canvas — a mistyped name, or one that expired (24 h sliding TTL) or was dropped. Other values are possible when a failure originates below the handler."
  3. 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_not_enabled`: CANVAS_PROVIDER_TYPE is not set to duckdb `canvas_not_found`: The canvas_id is unknown or has expired (TTL is 24 h sliding) `system_catalog_access`: The SQL references a system catalog (information_schema, sqlite_master, pg_catalog, or a duckdb_*() function) `missing_table`: The SQL references a table that is not staged on this canvas — a mistyped name, or one that expired (24 h sliding TTL) or was dropped Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `canvas_not_enabled`: CANVAS_PROVIDER_TYPE is not set to duckdb. `canvas_not_found`: The canvas_id is unknown or has expired (TTL is 24 h sliding). `system_catalog_access`: The SQL references a system catalog (information_schema, sqlite_master, pg_catalog, or a duckdb_*() function). `missing_table`: The SQL references a table that is not staged on this canvas — a mistyped name, or one that expired (24 h sliding TTL) or was dropped. Other values are possible when a failure originates below the handler."
  4. 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",
+      "canvas_id"
+    ]
+  },
+  {
+    "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_not_enabled`: CANVAS_PROVIDER_TYPE is not set to duckdb `canvas_not_found`: The canvas_id is unknown or has expired (TTL is 24 h sliding) `system_catalog_access`: The SQL references a system catalog (information_schema, sqlite_master, pg_catalog, or a duckdb_*() function) `missing_table`: The SQL references a table that is not staged on this canvas — a mistyped name, or one that expired (24 h sliding TTL) or was dropped Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "canvas_not_enabled",
+            "canvas_not_found",
+            "system_catalog_access",
+            "missing_table"
+          ],
+          "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",
-  "canvas_id"
-]
  5. Changed1 schema field changed
    • changedInput schema / properties / canvas_id / description
      Previous value: -"Canvas ID returned by openmeteo_get_forecast, openmeteo_get_historical, openmeteo_get_ensemble, openmeteo_get_flood, or openmeteo_get_climate when truncated: true."New value: +"Canvas ID returned by openmeteo_get_forecast, openmeteo_get_historical, openmeteo_get_marine, openmeteo_get_air_quality, openmeteo_get_ensemble, openmeteo_get_flood, or openmeteo_get_climate when truncated: true."
  6. Changed1 schema field changed
    • changedInput schema / properties / canvas_id / description
      Previous value: -"Canvas ID returned by openmeteo_get_historical, openmeteo_get_ensemble, openmeteo_get_flood, or openmeteo_get_climate when truncated: true."New value: +"Canvas ID returned by openmeteo_get_forecast, openmeteo_get_historical, openmeteo_get_ensemble, openmeteo_get_flood, or openmeteo_get_climate when truncated: true."
  7. Changed1 schema field changed
    • changedInput schema / properties / canvas_id / description
      Previous value: -"Canvas ID returned by openmeteo_get_historical, openmeteo_get_ensemble, or openmeteo_get_climate when truncated: true."New value: +"Canvas ID returned by openmeteo_get_historical, openmeteo_get_ensemble, openmeteo_get_flood, or openmeteo_get_climate when truncated: true."
  8. Changed1 schema field changed
    • changedOutput schema / properties / rows / description
      Previous value: -"Result rows (capped at the canvas row limit, default 10 000)."New value: +"Result rows — a preview capped at 100. When row_count exceeds this, page the rest by re-issuing the SQL with LIMIT / OFFSET."
  9. Changed1 schema field changed
    • changedInput schema / properties / canvas_id / description
      Previous value: -"Canvas ID returned by openmeteo_get_historical or openmeteo_get_ensemble when truncated: true."New value: +"Canvas ID returned by openmeteo_get_historical, openmeteo_get_ensemble, or openmeteo_get_climate when truncated: true."
  10. Changed1 schema field changed
    • changedInput schema / properties / canvas_id / description
      Previous value: -"Canvas ID returned by openmeteo_get_historical when truncated: true."New value: +"Canvas ID returned by openmeteo_get_historical or openmeteo_get_ensemble when truncated: true."
  11. Added

TDQS

A4.6/5.0
Behavior4/5

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

readOnlyHint=true already covers the safety profile, and the description adds real operational context: a 100-row leading cap, the 80,000-character inline ceiling that can lower it, and a row_count that may be a lower bound flagged by count_error when counting fails or exceeds 5 seconds. Because an output schema exists, some of this return-value detail is duplicative of structured data, keeping it just below a 5.

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

Conciseness4/5

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

Front-loads the verb+resource in the first clause, then layers precondition, discovery path, and return behavior. The final sentence is long and packed with caveats, but every clause carries distinct information, so nothing is wasted.

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?

Covers the full lifecycle an agent needs: how tables get staged, how to obtain canvas_id/table_name, how to discover names, and how results and row counts behave. With an output schema and readOnlyHint present, no significant gap remains.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds provenance semantics the schema cannot: canvas_id must come from a truncated: true spill and sql must reference the exact table_name those tools returned. That is meaningful added meaning over the two field descriptions.

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 (run a read-only SQL SELECT) and resource (tables staged on a DataCanvas by the named openmeteo_get_* tools), and explicitly differentiates itself from siblings by naming openmeteo_dataframe_describe for discovery and the seven staging tools as producers.

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?

Gives the exact precondition for use (pass the canvas_id returned when any get_* tool spills with truncated: true, reference the exact table_name returned alongside it) and routes the agent to openmeteo_dataframe_describe when names are unknown. It even closes with paging guidance via LIMIT/OFFSET.

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

All open-meteo-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