Fetch any URL as markdown, text, HTML or selector-built JSON; search Google, Bing, Yahoo and Brave.
Maintained bywebfetch.io(verified)Also a maintainer?
Call this server's tools from your browser. Nothing to install.
Your webfetch.io API key as a Bearer token. Free key at https://webfetch.io/signup
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Fetch a URL and return JSON built from CSS or XPath selectors, so the model receives structured fields instead of a whole page.
The absolute http or https URL to fetch.
Map a name to a selector. A string is shorthand for the text of the first match, and "a@href" takes an attribute. An object may set selector, selector_type (auto, css, xpath), type (item or list), and output (text, html, @attr, table_json, table_array, or a nested object of further rules). Example: {"titles": {"selector": "h2", "type": "list"}}
Render in a browser before extracting.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http webfetch https://webfetch.io/mcp \ --header 'Authorization: Bearer YOUR_TOKEN'
Headers
Authorization (required): Your webfetch.io API key as a Bearer token. Free key at https://webfetch.io/signupFetch a URL and return JSON built from CSS or XPath selectors, so the model receives structured fields instead of a whole page.
| Argument | Type | Description |
|---|---|---|
| url* | string | The absolute http or https URL to fetch. |
| render_js | boolean | Render in a browser before extracting. |
| extract_rules* | object | Map a name to a selector. A string is shorthand for the text of the first match, and "a@href" takes an attribute. An object may set selector, selector_type (auto, css, xpath), type (item or list), and output (text, html, @attr, table_json, table_array, or a nested object of further rules). Example: {"titles": {"selector": "h2", "type": "list"}} |
{
"type": "object",
"required": [
"url",
"extract_rules"
],
"properties": {
"url": {
"type": "string",
"description": "The absolute http or https URL to fetch."
},
"render_js": {
"type": "boolean",
"default": true,
"description": "Render in a browser before extracting."
},
"extract_rules": {
"type": "object",
"description": "Map a name to a selector. A string is shorthand for the text of the first match, and \"a@href\" takes an attribute. An object may set selector, selector_type (auto, css, xpath), type (item or list), and output (text, html, @attr, table_json, table_array, or a nested object of further rules). Example: {\"titles\": {\"selector\": \"h2\", \"type\": \"list\"}}"
}
}
}Fetch a URL and return its content as markdown, plain text or raw HTML. JavaScript is rendered by default, which costs 5 credits; set render_js to false for a plain HTTP fetch at 1 credit. A failed fetch costs nothing.
| Argument | Type | Description |
|---|---|---|
| url* | string | The absolute http or https URL to fetch. |
| render_js | boolean | Render in a browser. False is cheaper and faster but misses anything drawn by JavaScript. |
| return_format | string | markdown and text strip the page chrome and are what a model usually wants. html returns the document unchanged. |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "The absolute http or https URL to fetch."
},
"render_js": {
"type": "boolean",
"default": true,
"description": "Render in a browser. False is cheaper and faster but misses anything drawn by JavaScript."
},
"return_format": {
"enum": [
"markdown",
"text",
"html"
],
"type": "string",
"default": "markdown",
"description": "markdown and text strip the page chrome and are what a model usually wants. html returns the document unchanged."
}
}
}Run a search on Google, Bing, Yahoo and Brave and return one page of ranked results as JSON: organic results with title, URL and snippet, the ads, related searches and questions. 10 credits per page (15 with light_request false). Needs the robots.txt opt-out turned on for the key: paid plans turn it on in the key portal, and free accounts request search access there. A failed search costs nothing.
| Argument | Type | Description |
|---|---|---|
| page | integer | Results page. |
| query* | string | What to search for, as typed in the search box. |
| engine | string | The search engine. |
| search_type | string | classic for the full page, ads for the ads only. |
| country_code | string | Two-letter country to search from. |
| light_request | boolean | False loads the page in a browser, which on Bing includes the ads, at 15 credits. |
{
"type": "object",
"required": [
"query"
],
"properties": {
"page": {
"type": "integer",
"default": 1,
"maximum": 50,
"minimum": 1,
"description": "Results page."
},
"query": {
"type": "string",
"description": "What to search for, as typed in the search box."
},
"engine": {
"enum": [
"google",
"bing",
"yahoo",
"brave"
],
"type": "string",
"default": "google",
"description": "The search engine."
},
"search_type": {
"enum": [
"classic",
"ads"
],
"type": "string",
"default": "classic",
"description": "classic for the full page, ads for the ads only."
},
"country_code": {
"type": "string",
"default": "us",
"description": "Two-letter country to search from."
},
"light_request": {
"type": "boolean",
"default": true,
"description": "False loads the page in a browser, which on Bing includes the ads, at 15 credits."
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 22, 2026.
What changed in this server's tools since we started watching, newest first. Each change is scanned again.