PubChem MCP Server

get_external_references

Retrieve links to external chemical databases like ChEMBL, DrugBank, and KEGG for PubChem compounds to access additional research data and cross-reference chemical information.

Instructions

Get links to external databases (ChEMBL, DrugBank, KEGG, etc.)

Input Schema

TableJSON Schema

Name	Required	Description	Default
`cid`	Yes	PubChem Compound ID (CID)

Implementation Reference

src/index.ts:1195-1197 (handler)
The main handler function for the 'get_external_references' tool. It currently serves as a placeholder, returning a message that the feature is not yet implemented.
```
private async handleGetExternalReferences(args: any) {
  return { content: [{ type: 'text', text: JSON.stringify({ message: 'External references not yet implemented', args }, null, 2) }] };
}
```

src/index.ts:685-695 (registration)

Tool registration in the setTools call, including name, description, and input schema definition.

{
  name: 'get_external_references',
  description: 'Get links to external databases (ChEMBL, DrugBank, KEGG, etc.)',
  inputSchema: {
    type: 'object',
    properties: {
      cid: { type: ['number', 'string'], description: 'PubChem Compound ID (CID)' },
    },
    required: ['cid'],
  },
},

src/index.ts:688-694 (schema)

Input schema definition for the tool, specifying the required 'cid' parameter.

inputSchema: {
  type: 'object',
  properties: {
    cid: { type: ['number', 'string'], description: 'PubChem Compound ID (CID)' },
  },
  required: ['cid'],
},

src/index.ts:802-803 (registration)
Dispatcher switch case that routes calls to the specific handler function.
```
case 'get_external_references':
  return await this.handleGetExternalReferences(args);
```

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 29, 2025

TDQS

C2.9/5.0

Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action 'Get links' but doesn't describe what the output looks like (e.g., format, structure), whether it's a read-only operation, potential rate limits, or error handling. This is inadequate for a tool with zero annotation coverage.

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 a single, efficient sentence with zero waste. It front-loads the purpose and includes relevant examples (ChEMBL, DrugBank, KEGG) without unnecessary elaboration. Every word earns its place.

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

Completeness2/5

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

Given the complexity of retrieving external database links, no annotations, and no output schema, the description is incomplete. It lacks details on output format, behavioral traits, and usage context. This is a significant gap for a tool that likely returns structured data from multiple sources.

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 description coverage is 100%, with the parameter 'cid' clearly documented as 'PubChem Compound ID (CID)'. The description doesn't add any parameter details beyond what the schema provides, such as examples or constraints. Baseline 3 is appropriate since the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Get' and resource 'links to external databases', specifying examples like ChEMBL, DrugBank, and KEGG. It distinguishes from siblings by focusing on external database links rather than properties, bioactivities, or other compound data. However, it doesn't explicitly contrast with similar tools like 'get_literature_references' or 'get_compound_info'.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives. It doesn't mention prerequisites, context for selecting external databases, or how it differs from sibling tools like 'get_compound_info' or 'get_literature_references'. The description implies usage for external links but offers no explicit when/when-not instructions.

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