Low Risk

get_page_by_path

Retrieve a page from a GitBook space using its path instead of page ID

How to control get_page_by_path ↓

What get_page_by_path does on GitBook MCP Server

AI agents call get_page_by_path to retrieve information from GitBook MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why get_page_by_path needs a policy

This tool retrieves documentation content by path lookup—a read-only query operation with no side effects. It fits the 'Read' category: retrieves data without modifying, deleting, or executing external operations. Severity is low because the blast radius of retrieval-only access is minimal; an AI agent can only read existing documentation.

From the tool's definition Tool name 'get_page_by_path' and description 'Retrieve a page from a GitBook space' indicate data retrieval. Sibling tools (get_collection, get_file, get_page_content, get_space_content, list_*) are all read-only query operations.

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

How to control get_page_by_path

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

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

get_page_by_path 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 GitBook MCP Server — 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.

Related tools and policies

Go deeper

Questions about get_page_by_path

What does the get_page_by_path tool do? +

Retrieve a page from a GitBook space using its path instead of page ID. It is categorised as a Read tool in the GitBook MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_page_by_path? +

Register the GitBook MCP Server MCP server in PolicyLayer and add a rule for get_page_by_path: 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 GitBook MCP Server. Nothing to install.

What risk level is get_page_by_path? +

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

Can I rate-limit get_page_by_path? +

Yes. Add a rate_limit block to the get_page_by_path 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 get_page_by_path completely? +

Set action: deny in the PolicyLayer policy for get_page_by_path. 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 get_page_by_path? +

get_page_by_path is provided by the GitBook MCP Server MCP server (rickysullivan/gitbook-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every GitBook MCP Server tool call.

Start from GitBook MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

12 GitBook MCP Server tools catalogued and risk-classified — across an index of 43,000+ 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.