get_page

THE RISK

Low Risk

Why get_page needs a policy

This tool retrieves and queries page data by identifier, which is characteristic of Read operations. No data is created, modified, deleted, or executed. The blast radius is minimal since read access to documentation pages poses low risk to system integrity. Confidence is high because the description is explicit and unambiguous.

From the tool's definition Tool description states 'Get details and content of a specific page by ID' — a retrieval operation with no modification or side effects.

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

POLICY

How to control get_page

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_page": {}
  }
}

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

Create a free account and register Docmost MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Docmost MCP Server tools

Destructive delete_page Delete a single page by ID. Destructive delete_pages Delete multiple pages at once. Useful for cleanup. Write create_page Create a new page with content (automatically moves it to the correct hierarchy). Write move_page Move a page to a new parent (nesting) or root. Essential for organizing pages created via Write update_page Update a page Read get_workspace Get the current Docmost workspace Read list_groups List all available groups in Docmost Read list_pages List pages in a space ordered by updatedAt (descending).

All 11 Docmost MCP Server tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about get_page

What does the get_page tool do? +

Get details and content of a specific page by ID. It is categorised as a Read tool in the Docmost MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_page? +

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

What risk level is get_page? +

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

Can I rate-limit get_page? +

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

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

get_page is provided by the Docmost MCP Server MCP server (mrmartinimo/docmost-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Docmost MCP Server tool call.

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

CHECK YOUR STACK →