Connect Prerender to Claude, ChatGPT, Cursor, Claude Code, Codex, Gemini, GitHub Copilot and any other MCP client, for your whole team. Metorial adds security, governance, and tracing, and gives everyone one Magic MCP URL to connect.
Ask your agent in plain language. Each of these maps to a real tool on the server.
Use the recache urls tool in Prerender
Use the render page tool in Prerender
Use the manage sitemaps tool in Prerender
Use the clear cache tool in Prerender
Use the search cache tool in Prerender
Use the set recache speed tool in Prerender
Supported Tools
recache_urls
Recache URLs
Trigger caching or recaching of one or more URLs to ensure search engines see up-to-date content. Instead of waiting for cache expiration, use this to immediately refresh high-priority pages. Supports targeting desktop or mobile rendering.
render_page
Render Page
Render a URL through Prerender's headless browser and retrieve the fully rendered HTML and a downloadable HTML snapshot. This uses the core rendering service endpoint to produce a pre-rendered HTML snapshot of a JavaScript-heavy page.
manage_sitemaps
Manage Sitemaps
Submit, list, update, delete, or trigger a crawl for XML sitemaps in Prerender. Sitemaps allow Prerender to automatically discover and cache all listed URLs. New URLs from sitemaps are added to the rendering queue and rechecked on a configurable interval.
clear_cache
Clear Cache
Clear cached URLs from Prerender using a wildcard query pattern. Use `%` and `?` as SQL-like wildcards — for example, `https://example.com%` clears all cached URLs starting with that prefix. The clear job is scheduled asynchronously. You can optionally check the job status.
search_cache
Search Cache
Search for cached URLs in your Prerender account and view their cache status. Use a contains query to find partial matches, or an exact match to find a specific URL. Results can be filtered by adaptive type (desktop/mobile) and paginated.
set_recache_speed
Set Recache Speed
Control the speed at which Prerender recaches pages by setting the number of URLs rendered per hour. Higher values recache faster (up to 36,000/hour), lower values recache slower. Setting to 0 reverts to the automatic default. Returns recache metrics showing anticipated rendering frequency.
manage_domains
Manage Domains
View and manage connected domains in Prerender. List all domains with cache statistics, view or update domain-specific configuration such as cache lifetime, or get aggregate domain statistics.
submit_sitemap
Submit Sitemap
Submit an XML sitemap to add new URLs to the rendering queue. Existing cached URLs are not recached; use recache_urls to refresh them.
get_clear_cache_status
Get Clear Cache Status
Check whether a previously scheduled cache-clear job is still in progress, without scheduling another clear operation.
Enable Prerender in Metorial. In your Metorial portal, enable the Prerender MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
Add a custom connector. Open Customize, then Connectors. Select Add, then Custom, then Web.
Paste your Metorial MCP URL. Name it Metorial, paste your Magic MCP URL (<your-magic-mcp-url>) and continue.
Sign in. Select Add and sign in to load Prerender tools.
Enable Prerender in Metorial. In your Metorial portal, enable the Prerender MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
Add a custom MCP server. On ChatGPT web, open Plugins, select +, then Add custom MCP server.
Paste your Metorial MCP URL. Name it Metorial, paste your Magic MCP URL (<your-magic-mcp-url>), choose OAuth and accept the risk notice.
Create and install the plugin. Select Create as a plugin, install it and sign in to load Prerender tools.
Enable Prerender in Metorial. In your Metorial portal, enable the Prerender MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
Add Metorial to your MCP config. Use ~/.cursor/mcp.json for every project, or .cursor/mcp.json for one.
Sign in. Open Customize in the sidebar, find Metorial and sign in to load Prerender tools.
{
"mcpServers":{
"metorial":{
"url":"<your-magic-mcp-url>"
}
}
}
Enable Prerender in Metorial. In your Metorial portal, enable the Prerender MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
Add the server over HTTP. Add --scope user to use it in every project.
Sign in. Run /mcp, select Metorial and sign in to load Prerender tools.
claude mcp add --transport http metorial <your-magic-mcp-url>
Enable Prerender in Metorial. In your Metorial portal, enable the Prerender MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
Add the server and sign in. The Codex CLI, IDE extension and ChatGPT desktop app share this config.
Check the connection. Type /mcp in Codex to see Metorial and its Prerender tools.
codex mcp add metorial --url <your-magic-mcp-url>
codex mcp login metorial
Run Prerender through the Metorial gateway
One governed layer for every app your agents reach, not a separate connector per tool.
Give Prerender and every other app to your whole team through one MCP gateway, behind your SSO.
Scope which teams and agents can use Prerender tools with role-based access control, and trace every call.
Prefer to run it yourself? Metorial is open source and self-hostable.
Manage pre-rendered HTML cache for JavaScript-heavy websites to improve SEO. Recache single or multiple URLs on demand, search cached URLs by query or exact match, clear cache using wildcard patterns, submit and manage XML sitemaps for automated crawling, control recache speed, manage connected domains, and render pages through a headless browser. Supports desktop and mobile adaptive rendering.
Frequently asked questions
Common questions about connecting Prerender to AI agents with Metorial.
How many tools does the Prerender MCP server have?
The Prerender MCP server exposes 9 tools, including Recache URLs, Render Page, Manage Sitemaps. Each one is governed and traced through Metorial.
Does the Prerender MCP server support triggers?
Prerender exposes tools your agents call on demand; it does not publish event triggers yet. Everything still runs through one governed MCP URL.
Which AI clients can use the Prerender MCP server?
Any MCP client, including VS Code, Windsurf, Zed, OpenCode and Grok. Each one reaches the Prerender MCP server through the same Metorial URL.
How do I give only some teams access to Prerender?
Use role-based access control to decide which teams, users, and agents can use Prerender and which of its tools they can call.
Can I self-host the Prerender MCP server?
Yes. Metorial is open source, so you can run the Prerender MCP server yourself or use the hosted gateway.
Connect Prerender to production AI agents
See how Metorial gives your team governed access to Prerender, with tracing and security controls built in.