Skip to main content
Glama

chembl-mcp-server

by io.github.cyanheads
OverviewDiscussionsAdmin

chembl-dataframe-query

chembl_dataframe_query
Read-onlyIdempotent

Run a read-only SQL SELECT over the bioactivity rows chembl_get_bioactivities spilled to a canvas — rank, group, dedupe, and aggregate across the FULL set, not the inline preview. Reference each staged table by the name chembl_get_bioactivities returned — bioactivities for its potency_ranked view, bioactivities_null_potency for null_potency; discover the staged tables and their columns with chembl_dataframe_describe. Compute honest aggregates here (e.g. SELECT molecule_chembl_id, MEDIAN(pchembl_value) AS med FROM bioactivities WHERE standard_type = 'IC50' GROUP BY 1 ORDER BY 2 DESC). Two independent bounds apply, each reported on its own field: truncated is true when the SQL result exceeded the canvas row cap, and rendered_rows says how many of the returned rows the markdown table holds once its character budget is reached (below row_count on a wide or long result). Page past either bound with SQL LIMIT/OFFSET — append e.g. LIMIT 500 OFFSET 500 and re-call; offsets reach rows beyond the canvas row cap. Requires CANVAS_PROVIDER_TYPE=duckdb.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sqlYesA read-only SELECT against the staged tables. Reference tables by the names chembl_get_bioactivities returned.
canvas_idYesCanvas ID returned by chembl_get_bioactivities (spilled: true).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
rowsNoResult rows (capped at the canvas row limit). Each row is a column→value map.
errorNoPresent when the call failed. Absent on success.
row_countNoNumber of rows materialized in this response.
truncatedNoTrue when the SQL result exceeded the canvas row cap and was truncated — the engine bounding the result set itself, not the rendering. Independent of rendered_rows; page past it with LIMIT/OFFSET.
rendered_rowsNoHow many of those rows the markdown table in content[] holds. Below row_count when the rendered table reached its character budget — a rendering bound, INDEPENDENT of truncated: a response can be truncated:false and still render fewer rows than row_count. Re-run the same SQL with LIMIT/OFFSET to read the rows past it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / canvas_id / pattern
      Added value: +"^[A-Za-z0-9_-]{10}$"
  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",
+      "rendered_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`: Called while CANVAS_PROVIDER_TYPE is not duckdb, so no canvas exists. Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "canvas_disabled"
+          ],
+          "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",
-  "rendered_rows",
-  "truncated"
-]
  3. Changed3 schema fields changed
    • addedOutput schema / properties / rendered_rows
      Added value: +{
+  "description": "How many of those rows the markdown table in content[] holds. Below row_count when the rendered table reached its character budget — a rendering bound, INDEPENDENT of truncated: a response can be truncated:false and still render fewer rows than row_count. Re-run the same SQL with LIMIT/OFFSET to read the rows past it.",
+  "type": "number"
+}
    • changedOutput schema / properties / truncated / description
      Previous value: -"True when the SQL result exceeded the canvas row cap and was truncated."New value: +"True when the SQL result exceeded the canvas row cap and was truncated — the engine bounding the result set itself, not the rendering. Independent of rendered_rows; page past it with LIMIT/OFFSET."
    • changedOutput schema / required
      Previous value: -[
-  "rows",
-  "row_count",
-  "truncated"
-]New value: +[
+  "rows",
+  "row_count",
+  "rendered_rows",
+  "truncated"
+]
  4. First observed

TDQS

A5/5.0
Behavior5/5

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

The description goes well beyond the annotations by disclosing result cap behavior, the meaning of truncated and rendered_rows, paging semantics, and the CANVAS_PROVIDER_TYPE=duckdb requirement. It also confirms the read-only nature, consistent with readOnlyHint=true.

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 dense but front-loaded: the core purpose appears in the first sentence, followed by necessary details, an illustrative SQL example, cap semantics, and paging instructions. Every sentence adds operational value, and the structure leads the agent from purpose to invocation details.

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 SQL-query tool with two parameters and rich runtime constraints, this description is complete. It covers prerequisites (spilled canvas, duckdb), table discovery, query scope, result limits, and paging, while the output schema handles return-value documentation. Nothing critical is missing.

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

Parameters5/5

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

Although the input schema already covers both parameters, the description adds substantial meaning: how to reference staged tables, the expected SQL shape, that canvas_id must come from a spilled chembl_get_bioactivities result, and how LIMIT/OFFSET interacts with the caps. This goes far beyond the bare schema 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?

The description opens with a specific verb and resource: 'Run a read-only SQL SELECT over the bioactivity rows chembl_get_bioactivities spilled to a canvas.' It clearly states the operations (rank, group, dedupe, aggregate) and contrasts with 'the inline preview,' which helps distinguish it from the get_bioactivities sibling.

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 explicit guidance on when to use this tool: when you need full-set aggregation rather than inline preview. It names chembl_dataframe_describe as the discovery tool for staged tables and provides concrete SQL examples, plus a LIMIT/OFFSET pattern for paging beyond the canvas row cap.

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

All chembl-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