AI agents call find_related_entities to retrieve information from PubTator-MCP-Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve or query relationship data from the biomedical literature database without modifying, executing external code, deleting, or moving money. Despite the empty description lowering confidence slightly, the name and server purpose (annotation and relationship mining) strongly suggest a data retrieval function.
From the tool's definition Tool name 'find_related_entities' suggests querying relationships; server context indicates PubTator3 is a biomedical literature annotation/mining service focused on entity relationship discovery.
Documented attack patterns abuse exactly the kind of access find_related_entities gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PubTator-MCP-Server, and nothing reaches the server without passing your rules. This is the rule we recommend for find_related_entities:
{
"version": "1",
"default": "deny",
"tools": {
"find_related_entities": {}
}
}find_related_entities 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.
find_related_entities. It is categorised as a Read tool in the PubTator-MCP-Server MCP Server, which means it retrieves data without modifying state.
Register the PubTator-MCP-Server MCP server in PolicyLayer and add a rule for find_related_entities: 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 PubTator-MCP-Server. Nothing to install.
find_related_entities 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 find_related_entities 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 find_related_entities. 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.
find_related_entities is provided by the PubTator-MCP-Server MCP server (jackkuo666/pubtator-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from PubTator-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.
5 PubTator-MCP-Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.