AI agents call show_doc to retrieve information from DocAgent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays document content generated by the DocAgent system. It performs a read-only operation with no side effects, no code execution, no data modification, and no destructive capability. The low severity reflects that viewing documentation poses minimal risk even if accessed inappropriately—no irreversible changes, financial impact, or external system execution can occur.
From the tool's definition Tool name is 'show_doc' with description 'Show document content'. The verb 'show' indicates retrieval/display of existing data without modification or execution of external operations.
Attacks that exploit this kind of access
Show document content. It is categorised as a Read tool in the DocAgent MCP Server, which means it retrieves data without modifying state.
Register the DocAgent MCP server in PolicyLayer and add a rule for show_doc: 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 DocAgent. Nothing to install.
show_doc 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 show_doc 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 show_doc. 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.
show_doc is provided by the DocAgent MCP server (vinnyfds/docagent). 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 →