AI agents call get_term_children to retrieve information from OLS 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 existing data from the Ontology Lookup Service without creating, modifying, deleting, or executing anything. It is a straightforward read operation that returns child terms in an ontology hierarchy. No side effects or irreversible actions are possible. Low severity due to minimal blast radius—worst case is returning incorrect or irrelevant ontology data, which has limited operational impact.
From the tool's definition Tool name 'get_term_children' and description 'Get direct children of a specific term' indicate a retrieval operation with no modification or execution capabilities. It queries hierarchical relationships in biological/medical ontologies.
Documented attack patterns abuse exactly the kind of access get_term_children gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OLS MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_term_children:
{
"version": "1",
"default": "deny",
"tools": {
"get_term_children": {}
}
}get_term_children is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get direct children of a specific term. It is categorised as a Read tool in the OLS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OLS MCP Server MCP server in PolicyLayer and add a rule for get_term_children: 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 OLS MCP Server. Nothing to install.
get_term_children 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_term_children 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_term_children. 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_term_children is provided by the OLS MCP Server MCP server (seandavi/ols-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OLS MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 OLS MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.