# io.github.RodRomer/render-mcp

> Hosted browser for AI agents: screenshots, post-JS DOM, console, WCAG. No install, no API key.

- name: io.github.RodRomer/render-mcp
- version: 0.7.4
- connection class: unknown (unknown)
- trust: 66/100 flags: unreachable
- quality: 85/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.RodRomer%2Frender-mcp
- tools: https://api.protogrid.dev/v1/servers/io.github.RodRomer%2Frender-mcp/tools

**Not classified yet.** The remote endpoints have not been probed successfully, or the listing has nothing to connect to.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "render-mcp": {
      "type": "http",
      "url": "https://render.makermargins.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 5
- freshness: 85
- provenance: 90
- drivers: +repository +namespace-matches-repo +website -unreachable(3 failures) ~updated-48d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 85/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 86 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 6 of 6 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: rendered_html (destructiveHint, idempotentHint); page_diagnostics (destructiveHint, idempotentHint); accessibility_audit (destructiveHint, idempotentHint); …
- pass `tools.token_cost`: about 1,360 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 6, about 1,360 tokens to load them all
- tool set hash: 336783b3c6cf56239c2559a05756ab3c
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.RodRomer/render-mcp.svg)](https://protogrid.dev/servers/io.github.RodRomer/render-mcp)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://render.makermargins.com/mcp (streamable-http, auth none, reachable false, uptime30d 0.86868685)

## Packages

_none_

## Tools (6)

- `accessibility_audit`: Run a WCAG accessibility audit on a page using axe-core in a real browser, and report the violations with the elements responsible. Because it runs against a genuinely rendered page, colour-contrast and other rules that depend on layout and computed colour actually fire — these are silently skipped by audits that parse HTML without a layout engine. Use this to check a page meets WCAG before shipping.
- `inspect_element`: Answer 'why isn't this element showing where I expect?' for a CSS selector on a live page. Returns the resolved box model, computed display/visibility/opacity/position/z-index, colours, whether the element is inside the viewport, and — crucially — whether another element is covering it. These are the values a browser computes after the full cascade and layout; they cannot be derived from reading HTML and CSS.
- `page_diagnostics`: Load a page in a real browser and report what went wrong: JavaScript console errors and warnings, network requests that failed, and the HTTP status of the page itself. Use this when a site looks broken, a deployment might have shipped a bug, or a page loads blank and you need to know why. An agent cannot see a browser's console any other way.
- `rendered_html`: Fetch a page's HTML *after* JavaScript has executed. Use this when a plain HTTP fetch returns an empty shell or a loading spinner — single-page apps, sites that build their content client-side, or anything behind a framework. Returns the final DOM as HTML text.
- `screenshot_url`: Take a screenshot of a web page as it actually renders in a real browser, after JavaScript has run. Use this when you need to see a page rather than read it — checking a layout, confirming a site is up and looks right, or capturing what a user would actually see. Returns a PNG image.
- `url_to_pdf`: Render a web page to PDF exactly as a browser would print it. Use this to archive a page, produce a document from a rendered report, or capture something for a record. Returns a PDF file.