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 queries file contents within a restricted sandbox environment. It performs no reversible modifications, irreversible deletions, code execution, or financial operations. The sandbox restriction further limits blast radius. This is a straightforward Read operation with minimal risk.
From the tool's definition Tool description explicitly states 'Read a file from sandbox directory (text or pdf)'. The verb 'read' combined with the constrained scope (sandbox directory) indicates data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Read a file from sandbox directory (text or pdf). 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 →