Answer a question about a document by converting it to markdown and using Gemini.
AI agents call document_question_answering to retrieve information from Gemini Search MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information from a document and returns an answer. It reads and queries data without side effects, which is the defining characteristic of the Read category. The conversion to markdown is a presentational detail, not a destructive or mutative operation. Severity is low because misuse would only leak information already in the document, not cause system-wide harm.
From the tool's definition Tool name and description indicate 'answer a question about a document' — a retrieval and analysis operation with no modification, deletion, or code execution.
Attacks that exploit this kind of access
Answer a question about a document by converting it to markdown and using Gemini. It is categorised as a Read tool in the Gemini Search MCP MCP Server, which means it retrieves data without modifying state.
Register the Gemini Search MCP server in PolicyLayer and add a rule for document_question_answering: 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 Gemini Search MCP. Nothing to install.
document_question_answering 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 document_question_answering 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 document_question_answering. 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.
document_question_answering is provided by the Gemini Search MCP server (mimiclab/geminisearchmcp). 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 →