faostat-mcp-server

faostat-mcp-server: dataframe query

faostat_dataframe_query

Read-onlyIdempotent

Run a single-statement SELECT against the canvas tables staged by faostat_query_observations and faostat_commodity_profile (table names look like faostat_xxxxxxxx). Use this for cross-country and cross-item aggregation, GROUP BY rankings, joins, and time-series analysis over the full result set the inline preview only sampled. Standard DuckDB SQL — joins, aggregates, window functions, CTEs all work. Read-only: writes, DDL, DROP, COPY, PRAGMA, ATTACH, and external-file table functions are rejected; system catalogs (information_schema, sqlite_master, duckdb_*) are denied — list staged tables via faostat_dataframe_describe. Every row carries its data-quality flag — commonly A=Official, B=time-series break, E=Estimated, I=Imputed, M=Missing (value cannot exist), T=Unofficial, X=from an international organization, plus others FAOSTAT defines per domain — keep it in projections, treat any unrecognized flag as informational, and never assume it is official.

Input Schema

TableJSON Schema

Name	Required	Description
`sql`	Yes	Single-statement read-only SELECT against staged faostat_<id> tables. Columns: area_code, area, item_code, item, element_code, element, year, unit, value, flag — plus domain (QCL or TCL) on tables staged by faostat_commodity_profile.
`canvas_id`	No	Optional canvas ID as returned by a prior faostat_query_observations / faostat_commodity_profile call — exactly 10 characters of letters, digits, hyphens, and underscores. Omit to query the tables staged in this session (the common case).
`row_limit`	No	Hard cap on rows in the response. Default 1000, max 10000.

Output Schema

TableJSON Schema

Name	Required	Description
`rows`	No	Materialized result rows, bounded by row_limit.
`error`	No	Present when the call failed. Absent on success.
`notice`	No	Guidance when the query returned no rows or when results were capped.
`columns`	No	Column names in projection order.
`row_count`	No	Rows returned in this response — the materialized count, equal to rows.length. When truncated is true this is NOT the full result total (this path computes no exact total); page or aggregate to reach the rest.
`truncated`	No	True when row_limit capped the result and more rows exist than were returned. To reach them: page with ORDER BY + SQL LIMIT/OFFSET, raise row_limit (max 10000), or aggregate with GROUP BY.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 30, 2026

changedInput schema / properties / sql / description

Previous value: -"Single-statement read-only SELECT against staged faostat_<id> tables. Columns: area_code, area, item_code, item, element_code, element, year, unit, value, flag. CAST(value AS DOUBLE) for arithmetic."New value: +"Single-statement read-only SELECT against staged faostat_<id> tables. Columns: area_code, area, item_code, item, element_code, element, year, unit, value, flag — plus domain (QCL or TCL) on tables staged by faostat_commodity_profile."

Changed2 schema fields changedSep 19, 2026

changedInput schema / properties / canvas_id / description

Previous value: -"Optional canvas ID from a prior faostat_query_observations / faostat_commodity_profile call. Omit to query the tables staged in this session (the common case)."New value: +"Optional canvas ID as returned by a prior faostat_query_observations / faostat_commodity_profile call — exactly 10 characters of letters, digits, hyphens, and underscores. Omit to query the tables staged in this session (the common case)."

addedInput schema / properties / canvas_id / pattern
```
Added value: +"^[A-Za-z0-9_-]{10}$"
```

Changed6 schema fields changedAug 25, 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": [
+      "columns",
+      "row_count",
+      "rows",
+      "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`: The DataCanvas service is not configured for this deployment. `canvas_not_found`: An explicit canvas_id does not resolve to a live canvas — unknown, expired, or owned by another tenant. `missing_table`: The SQL references a faostat_<id> table that has expired or was never staged. `system_catalog_access`: The SQL references a denied system catalog (information_schema, sqlite_master, duckdb_*). `invalid_sql`: The SQL has a syntax or execution error, or is not a single read-only SELECT. Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "canvas_disabled",
+            "canvas_not_found",
+            "missing_table",
+            "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: -[
-  "columns",
-  "row_count",
-  "rows",
-  "truncated"
-]

Changed3 schema fields changedJul 13, 2026

changedOutput schema / properties / row_count / description

Previous value: -"Total rows the query produced (may exceed rows.length when capped)."New value: +"Rows returned in this response — the materialized count, equal to rows.length. When truncated is true this is NOT the full result total (this path computes no exact total); page or aggregate to reach the rest."

addedOutput schema / properties / truncated

Added value: +{
+  "description": "True when row_limit capped the result and more rows exist than were returned. To reach them: page with ORDER BY + SQL LIMIT/OFFSET, raise row_limit (max 10000), or aggregate with GROUP BY.",
+  "type": "boolean"
+}

changedOutput schema / required

Previous value: -[
-  "columns",
-  "row_count",
-  "rows"
-]New value: +[
+  "columns",
+  "row_count",
+  "rows",
+  "truncated"
+]

First observedJun 16, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Far exceeds the annotations: it enumerates rejected statements (writes, DDL, DROP, COPY, PRAGMA, ATTACH, external-file functions), denied catalogs (information_schema, sqlite_master, duckdb_*), and the read-only posture reinforcement. It also explains the data-quality `flag` semantics (A/B/E/I/M/T/X) and instructs the agent to keep flag in projections and not assume official — behavior an agent could not infer from readOnlyHint/idempotentHint alone.

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-loaded with the core action and immediately followed by use cases and the security envelope. Dense and mostly waste-free, though the long flag enumeration and the repeated safety framing make it slightly heavier than necessary.

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 query tool with 3 params, full schema coverage, an output schema, and read-only annotations, this is complete: it covers staging source, SQL dialect, security limits, table discovery route, and the flag column's meaning. An agent has everything needed to write and scope a valid query.

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 coverage is 100%, so the schema already documents sql, canvas_id, and row_limit. The description reinforces canvas usage ('tables staged in this session, the common case') but adds no syntax or format detail beyond the schema; the substantive added semantics (flag meanings) concern output columns, not parameters. Baseline 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?

States a specific verb and resource — 'Run a single-statement SELECT against the canvas tables staged by faostat_query_observations and faostat_commodity_profile' — and names the exact table-naming convention (faostat_xxxxxxxx). This clearly separates it from the sibling staging tools that produce the tables it queries.

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?

Gives explicit when-to-use cases: 'cross-country and cross-item aggregation, GROUP BY rankings, joins, and time-series analysis over the full result set the inline preview only sampled.' That sampling contrast tells the agent why to reach for this rather than the inline preview, but it names no exclusions or the sibling to use for other needs (e.g., faostat_dataframe_describe for listing).

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

All faostat-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.