kegg-mcp-server

get_drug_interactions

Read-onlyIdempotent

Retrieve drug-drug interactions for one or more KEGG drug IDs and limit returned results to support interaction screening.

Instructions

Get drug-drug interactions for one or more KEGG drugs.

Args: drug_ids: Single drug ID (e.g. 'D00001') or multiple IDs joined with '+' (e.g. 'D00001+D00564'). Max 10 entries. max_results: Maximum number of interactions to return (capped at 100).

Input Schema

Name	Required	Description	Default
`drug_ids`	Yes
`max_results`	No

Output Schema

Name	Required	Description	Default
`count`	Yes
`drug_ids`	Yes
`truncated`	No
`interactions`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed10 schema fields changedv0.5.0Oct 23, 2026

addedInput schema / properties / max_results

Added value: +{
+  "default": 100,
+  "title": "Max Results",
+  "type": "integer"
+}

removedOutput schema / $defs / DrugInteractionResult

Removed value: -{
-  "properties": {
-    "count": {
-      "title": "Count",
-      "type": "integer"
-    },
-    "drug_ids": {
-      "items": {
-        "type": "string"
-      },
-      "title": "Drug Ids",
-      "type": "array"
-    },
-    "interactions": {
-      "items": {
-        "$ref": "#/$defs/DrugInteraction"
-      },
-      "title": "Interactions",
-      "type": "array"
-    }
-  },
-  "required": [
-    "drug_ids",
-    "interactions",
-    "count"
-  ],
-  "title": "DrugInteractionResult",
-  "type": "object"
-}

removedOutput schema / $defs / ErrorResult

Removed value: -{
-  "description": "Structured error returned by a tool when the KEGG API fails.\n\nA tool returns this instead of raising so the model can reason about\nthe failure and decide whether to retry, change inputs, or give up.\nA point lookup that receives a 404 uses code ``not_found``; an empty search\nremains a successful result with no items.",
-  "properties": {
-    "code": {
-      "default": "kegg_api_error",
-      "title": "Code",
-      "type": "string"
-    },
-    "error": {
-      "title": "Error",
-      "type": "string"
-    },
-    "hint": {
-      "anyOf": [
-        {
-          "type": "string"
-        },
-        {
-          "type": "null"
-        }
-      ],
-      "default": null,
-      "title": "Hint"
-    },
-    "path": {
-      "anyOf": [
-        {
-          "type": "string"
-        },
-        {
-          "type": "null"
-        }
-      ],
-      "default": null,
-      "title": "Path"
-    },
-    "retryable": {
-      "default": false,
-      "title": "Retryable",
-      "type": "boolean"
-    },
-    "status": {
-      "anyOf": [
-        {
-          "type": "integer"
-        },
-        {
-          "type": "null"
-        }
-      ],
-      "default": null,
-      "title": "Status"
-    }
-  },
-  "required": [
-    "error"
-  ],
-  "title": "ErrorResult",
-  "type": "object"
-}

addedOutput schema / properties / count

Added value: +{
+  "title": "Count",
+  "type": "integer"
+}

addedOutput schema / properties / drug_ids

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "title": "Drug Ids",
+  "type": "array"
+}

addedOutput schema / properties / interactions

Added value: +{
+  "items": {
+    "$ref": "#/$defs/DrugInteraction"
+  },
+  "title": "Interactions",
+  "type": "array"
+}

removedOutput schema / properties / result

Removed value: -{
-  "anyOf": [
-    {
-      "$ref": "#/$defs/DrugInteractionResult"
-    },
-    {
-      "$ref": "#/$defs/ErrorResult"
-    }
-  ],
-  "title": "Result"
-}

addedOutput schema / properties / truncated

Added value: +{
+  "default": false,
+  "title": "Truncated",
+  "type": "boolean"
+}

changedOutput schema / required

Previous value: -[
-  "result"
-]New value: +[
+  "drug_ids",
+  "interactions",
+  "count"
+]

changedOutput schema / title

Previous value: -"get_drug_interactionsOutput"New value: +"DrugInteractionResult"

First observedv0.1.0Jul 29, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare read-only, idempotent, open-world, non-destructive behavior, so the description does not need to restate safety. It usefully adds operational constraints—at most 10 drug entries and a 100-result cap—which are behavioral details beyond the annotations. It does not discuss error behavior for oversized inputs, but that is a minor gap.

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 two short, front-loaded sentences plus a compact args block. Every sentence contributes directly to correct invocation, with no filler or redundancy.

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 an output schema exists and annotations cover safety semantics, the description supplies the remaining critical input details: ID syntax, multi-ID joining, and result limits. It is nearly complete, with only minor omissions around invalid-input behavior or ordering.

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?

With 0% schema description coverage, the description carries the full burden and does so effectively: it gives a concrete single-ID example, the '+' joining syntax for multiple IDs, the 10-entry maximum, and the max_results cap of 100. It could go slightly further by restating the default for max_results or clarifying ordering semantics, but the essential meaning is covered.

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 states a specific verb and resource ('Get drug-drug interactions') scoped to KEGG drugs, which is clearly distinct from sibling tools like get_drug_info or search_drugs. It stops short of explicitly naming an alternative or contrasting with those siblings.

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

Usage Guidelines3/5

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

Usage is implied by the purpose (fetch interactions for known drug IDs), but there is no explicit when-to-use guidance, no mention of when to prefer get_drug_info or search_drugs, and no prerequisites or exclusions. This is adequate but leaves the agent to infer routing.

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