Low Risk

render_html_page

Render a self-contained themed HTML page from body content. No Docker required. Wraps your HTML in a design system with typography, depth tiers, cards, grids, KPIs, badges, and section navigation. IMPORTANT: body_html is the INNER content only — do NOT include <html>, <head>, or <body> tags. Use ...

Part of the Mcp Media Forge MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

AI agents call render_html_page to retrieve information from Mcp Media Forge without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though render_html_page only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

io-github-pavelguzenfeld-media-forge.yaml
tools:
  render_html_page:
    rules:
      - action: allow

See the full Mcp Media Forge policy for all 8 tools.

Tool Name render_html_page
Category Read
Risk Level Low

Agents calling read-class tools like render_html_page have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.

What does the render_html_page tool do? +

Render a self-contained themed HTML page from body content. No Docker required. Wraps your HTML in a design system with typography, depth tiers, cards, grids, KPIs, badges, and section navigation. IMPORTANT: body_html is the INNER content only — do NOT include <html>, <head>, or <body> tags. Use mf- prefixed CSS classes: mf-hero, mf-elevated, mf-card, mf-grid, mf-kpi, mf-badge-success, etc. Themes: swiss (clean docs), midnight (presentations), warm (reports), terminal (dev content). Call get_tool_guide('html_page') for design system reference and examples.. It is categorised as a Read tool in the Mcp Media Forge MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on render_html_page? +

Add a rule in your Intercept YAML policy under the tools section for render_html_page. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Mcp Media Forge MCP server.

What risk level is render_html_page? +

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

Can I rate-limit render_html_page? +

Yes. Add a rate_limit block to the render_html_page rule in your Intercept 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 render_html_page completely? +

Set action: deny in the Intercept policy for render_html_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 render_html_page? +

render_html_page is provided by the Mcp Media Forge MCP server (mcp-media-forge). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on Mcp Media Forge

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept
github.com/policylayer/intercept →
// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.