AI agents call search_document to retrieve information from OrigeneMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the tool name 'search_document' and the broader context of this server (a biomedical information retrieval platform with tools like clinvar_query_*, depmap_get_*, check_*_accessions), this appears to be a Read operation that queries documents without side effects. The empty description limits confidence, but the naming convention and sibling tools all perform non-destructive information retrieval.
From the tool's definition Tool name 'search_document' suggests querying or retrieving document contents. The description is empty, which reduces confidence, but the name structure (search_*) and context within a biomedical research platform (OrigeneMCP) strongly indicate a retrieval…
Documented attack patterns abuse exactly the kind of access search_document gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OrigeneMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for search_document:
{
"version": "1",
"default": "deny",
"tools": {
"search_document": {}
}
}search_document 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.
search_document. It is categorised as a Read tool in the OrigeneMCP MCP Server, which means it retrieves data without modifying state.
Register the Origene MCP server in PolicyLayer and add a rule for search_document: 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 OrigeneMCP. Nothing to install.
search_document 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_document 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_document. 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_document is provided by the Origene MCP server (gentel-lab/origenemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OrigeneMCP, 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.
439 OrigeneMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.