AI agents call search_open_targets to retrieve information from Gwas without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search query against the Open Targets Platform, a publicly accessible bioinformatics resource. It retrieves information about genes, diseases, and drugs without creating, modifying, deleting, or executing arbitrary operations. The action is a straightforward data lookup with no irreversible consequences or external state changes. This is a classic Read operation in a research context.
From the tool's definition Tool description explicitly states 'Search Open Targets Platform for genes, diseases, or drugs.' The verb 'search' and the read-only nature of querying an external database indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Search Open Targets Platform for genes, diseases, or drugs. It is categorised as a Read tool in the Gwas MCP Server, which means it retrieves data without modifying state.
Register the Gwas MCP server in PolicyLayer and add a rule for search_open_targets: 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 Gwas. Nothing to install.
search_open_targets 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 search_open_targets 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 search_open_targets. 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.
search_open_targets is provided by the Gwas MCP server (muslus/gwas-mcp). 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 →