AI agents call doc_read 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 retrieves and reads document content. It performs a query operation with no modification, deletion, or execution of external processes. It falls squarely into the Read category as a data retrieval function. Severity is low because reading documents has minimal blast radius—the worst outcome is information disclosure or misuse of retrieved data, which is less severe than modification or execution risks.
From the tool's definition Tool is described as an alias of 'doc.read', which is listed among information retrieval tools. The server description emphasizes 'document reading' and 'information retrieval' without side effects.
Attacks that exploit this kind of access
Alias of doc.read. 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_read: 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_read 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_read 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_read. 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_read 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 →