List the quantitative ligand interactions for a protein target in the Guide to PHARMACOLOGY (IUPHAR/BPS). Given a GtoPdb target id (from search_targets), returns the ligands acting on it with interaction type (Agonist/Antagonist/Inhibitor/etc.), action, and binding affinity (e.g. pKi/pIC50). Keyl...
AI agents call target_interactions to retrieve information from Guidetopharmacology without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | number | — | Max interactions to return (default 25). |
target_id | number | string | Yes | GtoPdb target id, e.g. 1797 for EGFR. |
Parameters from the server's own tool schema.
This tool retrieves and queries existing pharmacological data (ligand interactions, binding affinities, interaction types) from a read-only database. It has no side effects, does not modify data, execute code, delete records, or move funds. The blast radius of misuse is minimal — an agent could only retrieve already-published drug interaction data.
From the tool's definition Tool description states it 'List[s] the quantitative ligand interactions' and 'returns the ligands' — purely a retrieval operation. No mutation, deletion, or execution keywords present. Described as 'Keyless' access to a public pharmacology database.
Attacks that exploit this kind of access
List the quantitative ligand interactions for a protein target in the Guide to PHARMACOLOGY (IUPHAR/BPS). Given a GtoPdb target id (from search_targets), returns the ligands acting on it with interaction type (Agonist/Antagonist/Inhibitor/etc.), action, and binding affinity (e.g. pKi/pIC50). Keyless. It is categorised as a Read tool in the Guidetopharmacology MCP Server, which means it retrieves data without modifying state.
target_interactions accepts 2 parameters: limit, target_id. Required: target_id. The full parameter table on this page comes from the server's own tool schema.
Register the Guidetopharmacology MCP server in PolicyLayer and add a rule for target_interactions: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Guidetopharmacology. Nothing to install.
target_interactions is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the target_interactions rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for target_interactions. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
target_interactions is provided by the Guidetopharmacology MCP server (pipeworx-io/mcp-guidetopharmacology). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →