get_block_content

THE RISK

Low Risk

Why get_block_content needs a policy

This tool queries and returns the content of a block. It performs a read operation with no capability to modify, delete, or execute actions. The retrieval of block content poses minimal risk even if misused by an AI agent, as it only exposes existing data visibility.

From the tool's definition Tool name and description: 'Get content of a specific block by its ID' — retrieves data without modification or side effects.

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

POLICY

How to control get_block_content

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

policy.json

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

get_block_content 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 Notion API 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 Notion API MCP Server tools

Destructive delete_block Delete blocks Write add_content_blocks Add content blocks with positioning support Write add_todo Add a new todo with rich features Write archive_page Archive a Notion page Write create_database Create a new database with custom schema in a parent page Write create_page Create a new page in Notion Write restore_page Restore an archived Notion page Write update_block_content Update a block

All 17 Notion API 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_block_content

What does the get_block_content tool do? +

Get content of a specific block by its ID. It is categorised as a Read tool in the Notion API MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_block_content? +

Register the Notion API MCP Server MCP server in PolicyLayer and add a rule for get_block_content: 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 Notion API MCP Server. Nothing to install.

What risk level is get_block_content? +

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

Can I rate-limit get_block_content? +

Yes. Add a rate_limit block to the get_block_content 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_block_content completely? +

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

get_block_content is provided by the Notion API MCP Server MCP server (pbohannon/notion-api-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Notion API MCP Server tool call.

Start from Notion API 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 →