AI agents call docsray_peek to retrieve information from Docsray without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
docsray_peek is a read-only introspection tool that retrieves metadata about documents without side effects. It queries document properties to help users understand available options before deeper analysis. This is a classic Read category operation with minimal security risk.
From the tool's definition Tool provides 'quick document overview' with 'page count, format, available extraction formats, provider capabilities' — all informational queries with no modification, deletion, or execution.
Attacks that exploit this kind of access
Get quick document overview: page count, format, available extraction formats, provider capabilities. Use this first to understand what. It is categorised as a Read tool in the Docsray MCP Server, which means it retrieves data without modifying state.
Register the Docsray MCP server in PolicyLayer and add a rule for docsray_peek: 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 Docsray. Nothing to install.
docsray_peek 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 docsray_peek 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 docsray_peek. 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.
docsray_peek is provided by the Docsray MCP server (johnfkraus/docsray-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 →