AI agents call find_related_entries to retrieve information from Oh My KEGG MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name indicates retrieval of related entries from a biological database without modification. No arguments are visible that would suggest code execution, deletion, or financial operations. The pattern of sibling tools on this KEGG server are all read operations that search or retrieve data.
From the tool's definition Tool name 'find_related_entries' suggests a lookup/search operation. Description is empty. Context shows sibling tools are primarily read-only queries (batch_entry_lookup, get_compound_info, get_disease_info, get_drug_info, get_enzyme_info, etc.) on the KEGG…
Documented attack patterns abuse exactly the kind of access find_related_entries gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Oh My KEGG MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for find_related_entries:
{
"version": "1",
"default": "deny",
"tools": {
"find_related_entries": {}
}
}find_related_entries 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_entries. It is categorised as a Read tool in the Oh My KEGG MCP MCP Server, which means it retrieves data without modifying state.
Register the Oh My KEGG MCP server in PolicyLayer and add a rule for find_related_entries: 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 Oh My KEGG MCP. Nothing to install.
find_related_entries 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_entries 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_entries. 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_entries is provided by the Oh My KEGG MCP server (martinuslee/oh-my-kegg-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Oh My KEGG MCP, 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.
33 Oh My KEGG MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.