AI agents call docs_read to retrieve information from Access without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data (document content) without side effects. It does not create, modify, delete, or execute anything. The severity is low because reading document text has minimal blast radius—the worst case is exposure of information the agent was already authorized to access via the proxy's permissioning layer.
From the tool's definition Tool name is 'docs_read' and description states it 'Read[s] the full text content of a Google Doc' and 'Returns the document body as plain text.' The verb 'read' and 'extract' with no mention of modification, deletion, or execution confirms retrieval-only…
Attacks that exploit this kind of access
Read the full text content of a Google Doc. Returns the document body as plain text. Use this for quick content extraction without formatting. It is categorised as a Read tool in the Access MCP Server, which means it retrieves data without modifying state.
Register the Access MCP server in PolicyLayer and add a rule for docs_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 Access. Nothing to install.
docs_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 docs_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 docs_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.
docs_read is provided by the Access MCP server (scottpedia0/access). 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 →