html.to-markdown · MCP: Risk & Policy

WHAT IT DOES

What html.to-markdown does on Mcp

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

WHY IT NEEDS A POLICY

Why html.to-markdown needs a policy

This tool reads and transforms input data (HTML) into a different format (markdown) with no capability to modify external state, execute code, delete data, or commit financial transactions. The explicit mention that it does not fetch URLs and only processes provided HTML confirms it is a pure read/transform operation. Low severity because misuse would only produce incorrect text output.

From the tool's definition Tool performs HTML-to-markdown conversion on provided content with no side effects: 'Convert raw HTML you already have into clean reading markdown (no URL fetch)'. Strips and extracts content; operations are purely transformative and reversible.

Attacks that exploit this kind of access

Questions about html.to-markdown

What does the html.to-markdown tool do? +

Convert raw HTML you already have into clean reading markdown (no URL fetch). POST { html }. Strips scripts/nav/ads, extracts main content, preserves headings/links/lists. For fetching a live URL use url.clean instead. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on html.to-markdown? +

Register the MCP server in PolicyLayer and add a rule for html.to-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 Mcp. Nothing to install.

What risk level is html.to-markdown? +

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

Can I rate-limit html.to-markdown? +

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

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

html.to-markdown is provided by the MCP server (@2sio/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.