Low Risk

read_document

read_document

How to control read_document ↓

AI agents call read_document to retrieve information from Noapi Google Search without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

A 'read_document' operation retrieves or queries document data with no side effects. Although the description is empty, the tool's name, position in an information-gathering MCP server, and sibling tools all point to read-only functionality. The most severe consequence of misuse would be unauthorized access to documents, which is less critical than write, execute, or financial operations.

From the tool's definition Tool name 'read_document' is a read operation; the description is empty but the name and context within a search/information-gathering server (alongside tools like archive_webpage, check_feeds, google_books, google_finance) strongly indicate document…

Documented attack patterns abuse exactly the kind of access read_document gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and Noapi Google Search, and nothing reaches the server without passing your rules. This is the rule we recommend for read_document:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "read_document": {}
  }
}

read_document is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Noapi Google Search — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the read_document tool do? +

read_document. It is categorised as a Read tool in the Noapi Google Search MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on read_document? +

Register the Noapi Google Search MCP server in PolicyLayer and add a rule for read_document: 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 Noapi Google Search. Nothing to install.

What risk level is read_document? +

read_document is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit read_document? +

Yes. Add a rate_limit block to the read_document 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.

How do I block read_document completely? +

Set action: deny in the PolicyLayer policy for read_document. 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.

What MCP server provides read_document? +

read_document is provided by the Noapi Google Search MCP server (vincentkaufmann/noapi-google-search-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Noapi Google Search tool call.

Deterministic rules across all 38 Noapi Google Search tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

38 Noapi Google Search tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.