Skip to main content
Glama

Pubchem

by io.github.pipeworx-io

Get Classification

get_classification
Read-onlyIdempotent

Pharmacological classification tree for a CID — drug class, mechanism of action, biological role tags. Useful for "what kind of drug is X" questions.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cidYesPubChem Compound ID

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
cidYesPubChem Compound ID
pubchem_urlNoDirect URL to pharmacology section on PubChem
pharmacology_sectionsYesPharmacology classification sections with values

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed2 schema fields changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "cid": 3672
+  }
+]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "cid": {
+      "description": "PubChem Compound ID",
+      "type": "number"
+    },
+    "pharmacology_sections": {
+      "additionalProperties": {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "description": "Pharmacology classification sections with values",
+      "type": "object"
+    },
+    "pubchem_url": {
+      "description": "Direct URL to pharmacology section on PubChem",
+      "type": "string"
+    }
+  },
+  "required": [
+    "cid",
+    "pharmacology_sections"
+  ],
+  "type": "object"
+}
  2. First observed

TDQS

A4/5.0
Behavior3/5

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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false, covering safety and idempotency. The description adds that it returns a tree and tags, but does not elaborate on response structure or limits. Given annotations, the description adds marginal value.

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, no filler. The first sentence defines the tool precisely, the second gives a use case. Ideal length for quick comprehension.

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

Completeness4/5

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

Given the simple input, strong annotations, and existence of an output schema, the description is sufficiently complete for an agent to understand purpose and safe usage. It could hint at the hierarchical nature, but not necessary.

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% with a single parameter 'cid' described as 'PubChem Compound ID'. The description reinforces that the input is a CID but adds no additional meaning beyond the schema. Baseline score applies.

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 clearly states it returns a pharmacological classification tree including drug class, mechanism of action, and biological role tags for a PubChem Compound ID (CID). It is explicitly distinguished from sibling tools like get_compound or search_by_name by focusing on 'what kind of drug' questions.

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?

The description directly says 'Useful for...' which implies the appropriate context for use. It does not explicitly list when not to use or alternatives, but the specialization is clear enough given the sibling tool names. A minor gap remains.

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

All Pubchem toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0
Disambiguation2/5

Many tools overlap heavily: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, and deep_research all answer factual questions through similar routing; the polymarket_* tools and entity_profile/compare_entities/recent_changes also cover the same ground. The server is named Pubchem but most tools are unrelated, adding another layer of confusion.

Naming Consistency4/5

All tool names are snake_case and mostly follow verb_noun (search_by_name, get_compound, create_subscription, etc.). Minor deviations exist like entity_profile and recent_alerts being noun-first, and the pipeworx_*/polymarket_* prefixes make the set feel more like multiple products than one coherent API.

Tool Count2/5

35 tools is a large surface, and only 4 (search_by_name, get_compound, get_classification, get_synonyms) actually belong to PubChem. The other 31 tools form a broad Pipeworx/prediction-market toolkit that seems unrelated to the server's stated name and purpose.

Completeness2/5

For a PubChem server the coverage is minimal: basic name->CID resolution, compound properties, classification, and synonyms, but no formula search, bioassay, spectra, or list/search by other identifiers. The Pipeworx tools are extensive for general data querying but require accounts/keys for full use, so anonymous agents hit incomplete workflow dead ends.

Resources