Search for ontology terms by name
AI agents call search_ontology_by_name to retrieve information from Ensembl MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves ontology term information based on name searches. It performs a read-only lookup against the Ensembl genomics API with no side effects, data modification, or destructive operations. The blast radius of misuse is minimal—an agent could only retrieve unwanted genomic ontology data, which carries no financial, destructive, or operational risk.
From the tool's definition Tool name contains 'search' and description states 'Search for ontology terms by name' - purely a query operation with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Search for ontology terms by name. It is categorised as a Read tool in the Ensembl MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Ensembl MCP Server MCP server in PolicyLayer and add a rule for search_ontology_by_name: 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 Ensembl MCP Server. Nothing to install.
search_ontology_by_name 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_ontology_by_name 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_ontology_by_name. 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_ontology_by_name is provided by the Ensembl MCP Server MCP server (munch-group/ensembl-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 →