Medium Risk

import-markdown

Import Markdown content and convert to Tiptap JSON format

How to control import-markdown ↓

What import-markdown does on Tiptap Collaboration MCP Server

AI agents use import-markdown to create or update resources in Tiptap Collaboration MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tiptap Collaboration MCP Server environment.

Medium Risk

Why import-markdown needs a policy

The import operation creates new document content or modifies existing document state by converting and inserting markdown data into the Tiptap collaborative document system. This is a reversible write operation (content can be edited or documents deleted), not a read-only query, nor a destructive delete.

From the tool's definition Tool is named 'import-markdown' and described as 'Import Markdown content and convert to Tiptap JSON format'. This converts external markdown into the document system's internal format, creating or modifying document state.

Documented attack patterns abuse exactly the kind of access import-markdown gives an agent:

How to control import-markdown

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "import-markdown": {
      "limits": [
        {
          "counter": "import-markdown_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

import-markdown stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Tiptap Collaboration 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.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about import-markdown

What does the import-markdown tool do? +

Import Markdown content and convert to Tiptap JSON format. It is categorised as a Write tool in the Tiptap Collaboration MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on import-markdown? +

Register the Tiptap Collaboration MCP Server MCP server in PolicyLayer and add a rule for import-markdown: 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 Tiptap Collaboration MCP Server. Nothing to install.

What risk level is import-markdown? +

import-markdown is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit import-markdown? +

Yes. Add a rate_limit block to the import-markdown 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 import-markdown completely? +

Set action: deny in the PolicyLayer policy for import-markdown. 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 import-markdown? +

import-markdown is provided by the Tiptap Collaboration MCP Server MCP server (trainual/tiptap-collaboration-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Tiptap Collaboration MCP Server tool call.

Start from Tiptap Collaboration 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.

11 Tiptap Collaboration 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.