Faceabot Web page reader is an MCP server published by com.faceabot, hosted at faceabot.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 2 tools, including read_web_page, read_github_file.
Read any public web page as clean text, and files of public GitHub repositories. Free, no key.
60 connections through 4 shared values. Tap any node.
Reads a public web page and returns its title and main text as clean plain text (menus, scripts and ads removed), in pages of up to 50,000 characters. Use when: you need the content of an article, a documentation page, a blog post or any public page. Not for: pages that need a login; PDFs (use the Faceabot PDF tool). Example: {"url":"https://example.com"}
| Parameter | Type | Description |
|---|---|---|
| url * | string | Public https address of the page |
| start | integer | |
| max_chars | integer |
{
"name": "read_web_page",
"title": "Read a web page",
"description": "Reads a public web page and returns its title and main text as clean plain text (menus, scripts and ads removed), in pages of up to 50,000 characters.\nUse when: you need the content of an article, a documentation page, a blog post or any public page.\nNot for: pages that need a login; PDFs (use the Faceabot PDF tool).\nExample: {\"url\":\"https://example.com\"}",
"inputSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"examples": [
"https://example.com"
],
"description": "Public https address of the page"
},
"start": {
"type": "integer",
"default": 0,
"minimum": 0
},
"max_chars": {
"type": "integer",
"default": 15000,
"maximum": 50000,
"minimum": 500
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Returns a file from a public GitHub repository (default: its README). Use when: you need a project's README, documentation or source file. Example: {"repo":"cloudflare/workers-sdk","path":"README.md"}
| Parameter | Type | Description |
|---|---|---|
| ref | string | Branch, tag or commit. Default: the default branch |
| path | string | File path. Default: the README |
| repo * | string | owner/name, e.g. cloudflare/workers-sdk |
| start | integer | |
| max_chars | integer |
{
"name": "read_github_file",
"title": "Read a file from a public GitHub repository",
"description": "Returns a file from a public GitHub repository (default: its README).\nUse when: you need a project's README, documentation or source file.\nExample: {\"repo\":\"cloudflare/workers-sdk\",\"path\":\"README.md\"}",
"inputSchema": {
"type": "object",
"required": [
"repo"
],
"properties": {
"ref": {
"type": "string",
"description": "Branch, tag or commit. Default: the default branch"
},
"path": {
"type": "string",
"description": "File path. Default: the README"
},
"repo": {
"type": "string",
"examples": [
"cloudflare/workers-sdk"
],
"description": "owner/name, e.g. cloudflare/workers-sdk"
},
"start": {
"type": "integer",
"default": 0,
"minimum": 0
},
"max_chars": {
"type": "integer",
"default": 20000,
"maximum": 50000,
"minimum": 500
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Faceabot Reader: read any public web page as clean text (read_web_page {"url":…}) and files of public GitHub repositories (read_github_file {"repo":"owner/name"}). Free, no key. Pages that need a login cannot be read. PDFs: https://pdf.faceabot.com/mcp. YouTube transcripts: https://youtube.faceabot.com/mcp. Part of Faceabot (https://faceabot.com): any other tool: solve_need at https://faceabot.com/api/mcp.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.