Get homology information for proteins across species using STRING.
AI agents call get_homology to retrieve information from STRING MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only query operation that retrieves existing protein homology information from the STRING database. It has no side effects, does not execute arbitrary code, and does not modify or destroy data. The lowest blast radius applies since misuse would only result in querying the database repeatedly, not exposing sensitive operations or causing data loss.
From the tool's definition Tool name 'get_homology' and description 'Get homology information for proteins across species using STRING' indicate retrieval of pre-computed homology data with no modification or deletion of data.
Attacks that exploit this kind of access
Get homology information for proteins across species using STRING. It is categorised as a Read tool in the STRING MCP Server MCP Server, which means it retrieves data without modifying state.
Register the STRING MCP Server MCP server in PolicyLayer and add a rule for get_homology: 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 STRING MCP Server. Nothing to install.
get_homology 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 get_homology 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 get_homology. 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.
get_homology is provided by the STRING MCP Server MCP server (munch-group/string-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 →