AI agents call get_document_info to retrieve information from Fathom without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve metadata or information about a document without modifying, deleting, or executing code. The function name and context (a document collection server alongside other read-only query tools) indicates a retrieval operation with no side effects. The empty description prevents absolute certainty, but the naming pattern and server purpose strongly suggest this is a Read operation.
From the tool's definition Tool named 'get_document_info' on a document search/retrieval server; consistent with sibling tools like 'read_document', 'find_document', and 'search_documents' which are all read-only retrieval operations. Empty description lowers confidence slightly.
Attacks that exploit this kind of access
get_document_info. It is categorised as a Read tool in the Fathom MCP Server, which means it retrieves data without modifying state.
Register the Fathom MCP server in PolicyLayer and add a rule for get_document_info: 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 Fathom. Nothing to install.
get_document_info 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_document_info 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_document_info. 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_document_info is provided by the Fathom MCP server (romanshnurov/fathom-mcp). 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 →