Skip to main content
Glama

Ligand Interactions

ligand_interactions
Read-onlyIdempotent

What proteins a drug acts on, the curated target interactions for a ligand in the Guide to PHARMACOLOGY (IUPHAR/BPS), each with the target PROTEIN NAME, interaction type (Agonist/Antagonist/Inhibitor), action and binding affinity (pKi/pIC50). Pass the drug by name ("imatinib") and it is resolved for you; a GtoPdb ligand id also works. The response always names the ligand it actually read, so an id that turns out to be a different compound is visible rather than silent. Requires a GtoPdb API key, register free at guidetopharmacology.org/login.jsp and pass your own via _apiKey.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "ligand": "imatinib",
      "_apiKey": "your-guidetopharmacology-api-key"
    },
    "name": "ligand_interactions"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax interactions to return (default 25).
ligandNoDrug/ligand name, e.g. "imatinib". Resolved against the GtoPdb ligand list.
ligand_idNoGtoPdb ligand id, e.g. 4139 for aspirin. Optional, give this OR ligand.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / ligand_id / description
      Previous value: -"GtoPdb ligand id, e.g. 4139 for aspirin. Optional — give this OR ligand."New value: +"GtoPdb ligand id, e.g. 4139 for aspirin. Optional, give this OR ligand."
  2. Changed1 schema field changed
    • changedInput schema / examples
      Previous value: -[
      -  {
      -    "ligand": "imatinib"
      -  },
      -  {
      -    "ligand_id": 4139
      -  },
      -  {
      -    "ligand_id": "4139",
      -    "limit": 40
      -  }
      -]New value: +[
      +  {
      +    "_apiKey": "your-guidetopharmacology-api-key",
      +    "ligand": "imatinib"
      +  },
      +  {
      +    "_apiKey": "your-guidetopharmacology-api-key",
      +    "ligand_id": 4139
      +  },
      +  {
      +    "_apiKey": "your-guidetopharmacology-api-key",
      +    "ligand_id": "4139",
      +    "limit": 40
      +  }
      +]
  3. Changed4 schema fields changed
    • changedInput schema / examples
      Previous value: -[
      -  {
      -    "ligand_id": 4139
      -  },
      -  {
      -    "ligand_id": "4139",
      -    "limit": 40
      -  }
      -]New value: +[
      +  {
      +    "ligand": "imatinib"
      +  },
      +  {
      +    "ligand_id": 4139
      +  },
      +  {
      +    "ligand_id": "4139",
      +    "limit": 40
      +  }
      +]
    • addedInput schema / properties / ligand
      Added value: +{
      +  "description": "Drug/ligand name, e.g. \"imatinib\". Resolved against the GtoPdb ligand list.",
      +  "type": "string"
      +}
    • changedInput schema / properties / ligand_id / description
      Previous value: -"GtoPdb ligand id, e.g. 4139 for aspirin."New value: +"GtoPdb ligand id, e.g. 4139 for aspirin. Optional — give this OR ligand."
    • changedInput schema / required
      Previous value: -[
      -  "ligand_id"
      -]New value: +[]
  4. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
      +  {
      +    "ligand_id": 4139
      +  },
      +  {
      +    "ligand_id": "4139",
      +    "limit": 40
      +  }
      +]
  5. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, open-world, non-destructive, so the safety profile is covered. The description adds meaningful behavior beyond that: a mandatory self-registered API key with the registration URL, and the guarantee that the response echoes the ligand actually resolved so an id mapping to a different compound is visible rather than silent.

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?

The purpose is front-loaded in the first clause, followed by input modes, the echo-back caveat, and the auth prerequisite — a sensible descending order of importance. The single dense paragraph is efficient, though the API-key sentence could be split out for scannability.

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?

With no output schema, the description carries the burden of describing return content (protein name, interaction type, action, affinity) and it does so, plus documents the API-key prerequisite and the default limit via the schema. Minor gaps remain: no mention of pagination/truncation behavior at the limit or of an empty/unresolvable-ligand outcome.

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?

Schema coverage is 100%, so baseline would be 3, but the description adds semantics the schema does not: that `ligand` is name-resolved against the GtoPdb list, that `ligand_id` is an equally valid route, and that the resolved identity is echoed back for verification. It does not describe how resolution failures are surfaced, which keeps it below a 5.

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 names a specific resource (curated ligand–target interactions from IUPHAR/BPS Guide to PHARMACOLOGY) plus the fields returned (target protein name, interaction type, action, pKi/pIC50), so an agent knows exactly what it retrieves. It does not explicitly contrast itself with the sibling `target_interactions`, leaving the inverse-direction distinction to inference.

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?

It explains the two input modes clearly ('pass the drug by name and it is resolved for you; a GtoPdb ligand id also works'), which is real how-to-use guidance. However, it never states when this tool is preferable to alternatives or when not to use it, so the guidance is implied rather than explicit.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.