AI agents call doc.find to retrieve information from TOOL4LM without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs search and indexing operations on local documents within a sandbox directory. Searching and building indexes are read-class operations with no side effects on data integrity. The sandboxed scope limits exposure. Severity is low because search results cannot harm systems or create irreversible changes, though information disclosure is possible within the sandbox boundary.
From the tool's definition Tool description states 'Search local documents' and 'Builds index if missing' — these are read operations that retrieve or query data without modification. The function name contains 'find' which is a retrieval operation.
Attacks that exploit this kind of access
Search local documents within sandbox directory. Builds index if missing. It is categorised as a Read tool in the TOOL4LM MCP Server, which means it retrieves data without modifying state.
Register the TOOL4LM MCP server in PolicyLayer and add a rule for doc.find: 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 TOOL4LM. Nothing to install.
doc.find 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 doc.find 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 doc.find. 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.
doc.find is provided by the TOOL4LM MCP server (khanhs-234/tool4lm). 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 →