About pagerender
Pagerender provides packages for analyzing crawler extraction from HTML, auditing sitemap pages from the command line and exposing read-only tools to MCP clients. It is for users who need to inspect how search and AI crawlers process public pages.
Key features
- 01Analyze crawler extraction from HTML
- 02Audit sitemap pages from the CLI
- 03Expose nine read-only MCP tools
- 04Use five tools without a token
Use cases
- 01Inspect crawler extraction from an HTML string
- 02Audit pages listed in a sitemap
- 03Let an MCP client query public-page analysis
MCP support
The `@pagerender/mcp` package exposes nine read-only tools to MCP clients; five require no token. The README does not detail the individual tools.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @pagerender/mcpPAGERENDER_TOKENSecretA read-only Pagerender API key. Five of the nine tools work without it, and three of those make no network call to Pagerender at all.Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
9Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| url | string | Yes | The public URL to analyze. |
Details
From the project READMEPagerender tools
Three MIT packages from Pagerender, published together.
| Package | What it is |
|---|---|
@pagerender/analyze | What a search crawler extracts from an HTML string. No dependencies. |
@pagerender/cli | Audit every page in a sitemap from a shell. No account needed. |
@pagerender/mcp | Nine read-only tools for an MCP client, five of which need no token. |
npx @pagerender/cli audit --sitemap https://example.com/sitemap.xml --format table
This repository is generated
It is written by a script from the Pagerender monorepo, so a pull request against it cannot be merged directly. Open an issue, or write to https://pagerender.io/contact, and the change lands upstream and arrives here on the next release.
License
MIT.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.