AI agents call docsray_extract 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_extract is a retrieval and query operation that reads document content without creating, modifying, deleting, or executing operations. The ability to extract specific pages, tables, or images represents data retrieval only. No reversible or irreversible modifications are possible with this tool.
From the tool's definition Tool performs content extraction (markdown, text, JSON) from documents with no side effects. Description explicitly states 'Extract content' and 'Preserves formatting' with no mention of modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Extract content as markdown, text, or JSON. Extract specific pages, tables, or images. Preserves formatting. Fast for basic extraction, AI-powered for complex needs. 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_extract: 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_extract 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_extract 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_extract. 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_extract 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 →