Web pages as clean Markdown and JSON for AI agents, in fewer tokens, with an Evidence Record.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
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.
List a site's URLs without reading each page: the start page's links (read over HTTP alone) and the entries of the sitemaps the site declares, within one deadline. URLs stay in scope (the start host and its www twin, the start path's subtree, assets left out, similar URLs folded) and robots.txt applies unless ignoreRobotsTxt is set; what was left out is counted. No page title is fetched. At the deadline the answer is what was found (partial, stoppedBy timeout). Compact by default; debug adds each link's evidence and the sources read. Not for: reading pages, as one page body is read at most.
http(s) URL of the start page
The declared identity robots.txt, the page and the sitemaps are read under. authed is not offered: a map reads public sitemaps and one public page.
Return the full map response instead of the compact one.
Links returned at most. Default 5000; a hosted server takes up to 5000. Reaching it is status completed with stoppedBy limit.
Keep only the URLs in which every word (at most 10) appears, case-insensitively, in the decoded URL or its title. A filter, not a ranking: the order stays the discovery order, and limit counts the matches.
include (default): the start page's links and the sitemaps. skip: no sitemap is read. only: no page is read; the links are the sitemap entries in their listed order (the start URL only when a sitemap lists it).
Milliseconds for the whole map. Default 60000; a hosted server takes up to 60000.
Your workflow label (printable, no spaces); recorded, not sent to sites.
Pathname regexes that leave a URL out; they win over includePaths.
Pathname regexes a URL must match.
Match includePaths and excludePaths against the canonical URL instead of its pathname. Default false.
Admit URLs anywhere on the start host, not only in the start URL's path subtree. Default false.
Admit every host under the start URL's apex (the host with one leading www. removed; no public-suffix list). Default false. Each new host's robots.txt is read, for at most 20 hosts.
Fold URLs that differ only in their query string into the first one seen, returned without its query; each merge is counted (refused.collapsed, with samples under debug). Default false.
Fold /a and /a/, / and /index.html, www and apex, http and https into one URL. Default true.
List a site's URLs without reading each page: the start page's links (read over HTTP alone) and the entries of the sitemaps the site declares, within one deadline. URLs stay in scope (the start host and its www twin, the start path's subtree, assets left out, similar URLs folded) and robots.txt applies unless ignoreRobotsTxt is set; what was left out is counted. No page title is fetched. At the deadline the answer is what was found (partial, stoppedBy timeout). Compact by default; debug adds each link's evidence and the sources read. Not for: reading pages, as one page body is read at most.
| Argument | Type | Description |
|---|---|---|
| url* | string | http(s) URL of the start page |
| mode | string | The declared identity robots.txt, the page and the sitemaps are read under. authed is not offered: a map reads public sitemaps and one public page. |
| debug | boolean | Return the full map response instead of the compact one. |
| limit | integer | Links returned at most. Default 5000; a hosted server takes up to 5000. Reaching it is status completed with stoppedBy limit. |
| search | string | Keep only the URLs in which every word (at most 10) appears, case-insensitively, in the decoded URL or its title. A filter, not a ranking: the order stays the discovery order, and limit counts the matches. |
| sitemap | string | include (default): the start page's links and the sitemaps. skip: no sitemap is read. only: no page is read; the links are the sitemap entries in their listed order (the start URL only when a sitemap lists it). |
| timeout | integer | Milliseconds for the whole map. Default 60000; a hosted server takes up to 60000. |
| integration | string | Your workflow label (printable, no spaces); recorded, not sent to sites. |
| excludePaths | array | Pathname regexes that leave a URL out; they win over includePaths. |
| includePaths | array | Pathname regexes a URL must match. |
| regexOnFullURL | boolean | Match includePaths and excludePaths against the canonical URL instead of its pathname. Default false. |
| crawlEntireDomain | boolean | Admit URLs anywhere on the start host, not only in the start URL's path subtree. Default false. |
| includeSubdomains | boolean | Admit every host under the start URL's apex (the host with one leading www. removed; no public-suffix list). Default false. Each new host's robots.txt is read, for at most 20 hosts. |
| ignoreQueryParameters | boolean | Fold URLs that differ only in their query string into the first one seen, returned without its query; each merge is counted (refused.collapsed, with samples under debug). Default false. |
| deduplicateSimilarURLs | boolean | Fold /a and /a/, / and /index.html, www and apex, http and https into one URL. Default true. |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "http(s) URL of the start page"
},
"mode": {
"enum": [
"standard",
"research"
],
"type": "string",
"description": "The declared identity robots.txt, the page and the sitemaps are read under. authed is not offered: a map reads public sitemaps and one public page."
},
"debug": {
"type": "boolean",
"description": "Return the full map response instead of the compact one."
},
"limit": {
"type": "integer",
"maximum": 5000,
"minimum": 1,
"description": "Links returned at most. Default 5000; a hosted server takes up to 5000. Reaching it is status completed with stoppedBy limit."
},
"search": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "Keep only the URLs in which every word (at most 10) appears, case-insensitively, in the decoded URL or its title. A filter, not a ranking: the order stays the discovery order, and limit counts the matches."
},
"sitemap": {
"enum": [
"include",
"skip",
"only"
],
"type": "string",
"description": "include (default): the start page's links and the sitemaps. skip: no sitemap is read. only: no page is read; the links are the sitemap entries in their listed order (the start URL only when a sitemap lists it)."
},
"timeout": {
"type": "integer",
"maximum": 60000,
"minimum": 1000,
"description": "Milliseconds for the whole map. Default 60000; a hosted server takes up to 60000."
},
"integration": {
"type": "string",
"pattern": "^[\\x21-\\x7e]+$",
"maxLength": 100,
"minLength": 1,
"description": "Your workflow label (printable, no spaces); recorded, not sent to sites."
},
"excludePaths": {
"type": "array",
"items": {
"type": "string"
},
"description": "Pathname regexes that leave a URL out; they win over includePaths."
},
"includePaths": {
"type": "array",
"items": {
"type": "string"
},
"description": "Pathname regexes a URL must match."
},
"regexOnFullURL": {
"type": "boolean",
"description": "Match includePaths and excludePaths against the canonical URL instead of its pathname. Default false."
},
"crawlEntireDomain": {
"type": "boolean",
"description": "Admit URLs anywhere on the start host, not only in the start URL's path subtree. Default false."
},
"includeSubdomains": {
"type": "boolean",
"description": "Admit every host under the start URL's apex (the host with one leading www. removed; no public-suffix list). Default false. Each new host's robots.txt is read, for at most 20 hosts."
},
"ignoreQueryParameters": {
"type": "boolean",
"description": "Fold URLs that differ only in their query string into the first one seen, returned without its query; each merge is counted (refused.collapsed, with samples under debug). Default false."
},
"deduplicateSimilarURLs": {
"type": "boolean",
"description": "Fold /a and /a/, / and /index.html, www and apex, http and https into one URL. Default true."
}
},
"additionalProperties": false
}Read one URL as Markdown with its Evidence Record (final URL, fetch time, HTTP status, robots.txt decision, hashes), over HTTP first and in the browser when the page needs it. Not for: many URLs or a whole site section. Compact by default; debug adds the full audit. warnings name what the content cannot vouch for (client_rendered_suspected, robots_overridden), and agentHints the next step.
| Argument | Type | Description |
|---|---|---|
| url* | string | An http(s) URL. |
| mode | string | The declared identity the page is read under: standard (default) or research. A hosted server holds no saved logins, so it has no authed mode. |
| debug | boolean | Return the full audit: trace, ladderTrace and every attempt. |
| mobile | boolean | Read as declared mobile Chrome (Android UA, 412x915). Default false. |
| verify | object | Checks on final delivery; passed covers configured checks only. Inspect failure/readiness before retrying. Types: markdownIncludes, markdownMatches, markdownCountMin, minTables, tableRowsMin (tables format, zero-based columns), listRecordsMin, recordFields (uniqueBy counts complete extracted identities), field. Markdown checks need markdown format. |
| formats | array | What to return (default markdown): markdown, links, html, rawHtml, images, tables, json, attributes ({ selectors }), list ({ itemSelector?, fields? }: a record per repeated item, detected without itemSelector), screenshot or screenshot@fullPage (browser only). This connection has no browser lane, so it offers no screenshot. |
| headers | object | Extra headers to the page's origin, recorded; User-Agent, client hints, authorization and cookie are refused. |
| timeout | integer | Deadline in milliseconds for the whole scrape. When it fires the result is partial with the content so far, or failed/timeout. Here at most and by default 100000; a longer one is lowered to it. |
| blockAds | boolean | Block ad hosts and ad or cookie-banner elements in the browser. Default true. |
| fastMode | boolean | HTTP only: a page needing scripts returns the HTTP verdict (a shell is failed/empty_unverified). Default false. |
| excludeTags | array | CSS selectors removed with their contents. |
| includeTags | array | CSS selectors of the only elements to keep, whatever onlyMainContent says (no sibling combinators, :nth-child or :has). |
| integration | string | Your workflow label (printable, no spaces); recorded, not sent to sites. |
| includeLinks | boolean | Also return the page's outbound links. Default false. |
| maxFileBytes | integer | Largest file to download; a larger one is failed/body_too_large. |
| onlyMainContent | boolean | false keeps the whole page (header, navigation, footer). Default true. |
| allowlistedDomains | array |
| removeBase64Images | boolean | Drop data: URI images from the Markdown, keeping alt text. Default true. |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "An http(s) URL."
},
"mode": {
"enum": [
"standard",
"research"
],
"type": "string",
"description": "The declared identity the page is read under: standard (default) or research. A hosted server holds no saved logins, so it has no authed mode."
},
"debug": {
"type": "boolean",
"description": "Return the full audit: trace, ladderTrace and every attempt."
},
"mobile": {
"type": "boolean",
"description": "Read as declared mobile Chrome (Android UA, 412x915). Default false."
},
"verify": {
"type": "object",
"required": [
"checks"
],
"properties": {
"checks": {
"type": "array",
"items": {
"type": "object",
"required": [
"type"
],
"properties": {
"in": {
"type": "array",
"items": {
"type": [
"string",
"number",
"boolean",
"null"
]
},
"maxItems": 32,
"minItems": 1
},
"max": {
"type": "number"
},
"min": {
"type": "number"
},
"path": {
"type": "string",
"maxLength": 1000,
"minLength": 1
},
"text": {
"type": "string",
"maxLength": 1000,
"minLength": 1
},
"type": {
"enum": [
"markdownIncludes",
"minTables",
"tableRowsMin",
"listRecordsMin",
"recordFields",
"field"
],
"type": "string"
},
"flags": {
"type": "string",
"pattern": "^[imsuy]*$"
},
"equals": {
"type": [
"string",
"number",
"boolean",
"null"
]
},
"fields": {
"type": "array",
"items": {
"type": "string",
"maxLength": 1000,
"minLength": 1
},
"maxItems": 50,
"minItems": 1
},
"columns": {
"type": "array",
"items": {
"type": "integer",
"maximum": 1000000,
"minimum": 0
},
"maxItems": 50,
"minItems": 1,
"uniqueItems": true
},
"pattern": {
"type": "string",
"maxLength": 1000,
"minLength": 1
},
"present": {
"type": "boolean"
},
"uniqueBy": {
"type": "array",
"items": {
"type": "string",
"maxLength": 1000,
"minLength": 1
},
"maxItems": 50,
"minItems": 1,
"uniqueItems": true
},
"tableIndex": {
"type": "integer",
"maximum": 1000000,
"minimum": 0
}
},
"additionalProperties": false
},
"maxItems": 32,
"minItems": 1
},
"emptyOk": {
"type": "boolean",
"description": "An empty result (empty_verified, e.g. no search hits) passes. Default false."
}
},
"description": "Checks on final delivery; passed covers configured checks only. Inspect failure/readiness before retrying. Types: markdownIncludes, markdownMatches, markdownCountMin, minTables, tableRowsMin (tables format, zero-based columns), listRecordsMin, recordFields (uniqueBy counts complete extracted identities), field. Markdown checks need markdown format.",
"additionalProperties": false
},
"formats": {
"type": "array",
"items": {
"anyOf": [
{
"enum": [
"markdown",
"links",
"json",
"html",
"rawHtml",
"images",
"tables"
],
"type": "string"
},
{
"type": "object",
"required": [
"type",
"schema"
],
"properties": {
"type": {
"const": "json"
},
"prompt": {
"type": "string",
"maxLength": 4000
},
"schema": {
"type": "object"
},
"modelFallback": {
"type": "boolean"
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type",
"selectors"
],
"properties": {
"type": {
"const": "attributes"
},
"selectors": {
"type": "array",
"items": {
"type": "object",
"required": [
"selector",
"attribute"
],
"properties": {
"selector": {
"type": "string",
"maxLength": 200,
"minLength": 1
},
"attribute": {
"type": "string",
"pattern": "^[A-Za-z_][A-Za-z0-9_:.-]*$",
"maxLength": 100,
"minLength": 1
}
},
"additionalProperties": false
},
"maxItems": 50,
"minItems": 1
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"const": "list"
},
"fields": {
"type": "array",
"items": {
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"maxLength": 64,
"minLength": 1
},
"selector": {
"type": "string",
"maxLength": 200,
"minLength": 1
},
"attribute": {
"type": "string",
"pattern": "^[A-Za-z_][A-Za-z0-9_:.-]*$"
}
},
"additionalProperties": false
},
"maxItems": 50,
"minItems": 1
},
"itemSelector": {
"type": "string",
"maxLength": 200,
"minLength": 1
}
},
"additionalProperties": false
}
]
},
"minItems": 1,
"description": "What to return (default markdown): markdown, links, html, rawHtml, images, tables, json, attributes ({ selectors }), list ({ itemSelector?, fields? }: a record per repeated item, detected without itemSelector), screenshot or screenshot@fullPage (browser only). This connection has no browser lane, so it offers no screenshot."
},
"headers": {
"type": "object",
"description": "Extra headers to the page's origin, recorded; User-Agent, client hints, authorization and cookie are refused.",
"maxProperties": 32,
"additionalProperties": {
"type": "string",
"maxLength": 4096
}
},
"timeout": {
"type": "integer",
"maximum": 100000,
"minimum": 1000,
"description": "Deadline in milliseconds for the whole scrape. When it fires the result is partial with the content so far, or failed/timeout. Here at most and by default 100000; a longer one is lowered to it."
},
"blockAds": {
"type": "boolean",
"description": "Block ad hosts and ad or cookie-banner elements in the browser. Default true."
},
"fastMode": {
"type": "boolean",
"description": "HTTP only: a page needing scripts returns the HTTP verdict (a shell is failed/empty_unverified). Default false."
},
"excludeTags": {
"type": "array",
"items": {
"type": "string",
"maxLength": 200,
"minLength": 1
},
"maxItems": 100,
"description": "CSS selectors removed with their contents."
},
"includeTags": {
"type": "array",
"items": {
"type": "string",
"maxLength": 200,
"minLength": 1
},
"maxItems": 100,
"description": "CSS selectors of the only elements to keep, whatever onlyMainContent says (no sibling combinators, :nth-child or :has)."
},
"integration": {
"type": "string",
"pattern": "^[\\x21-\\x7e]+$",
"maxLength": 100,
"minLength": 1,
"description": "Your workflow label (printable, no spaces); recorded, not sent to sites."
},
"includeLinks": {
"type": "boolean",
"description": "Also return the page's outbound links. Default false."
},
"maxFileBytes": {
"type": "integer",
"maximum": 5242880,
"minimum": 1,
"description": "Largest file to download; a larger one is failed/body_too_large."
},
"onlyMainContent": {
"type": "boolean",
"description": "false keeps the whole page (header, navigation, footer). Default true."
},
"allowlistedDomains": {
"type": "array",
"items": {
"type": "string"
}
},
"removeBase64Images": {
"type": "boolean",
"description": "Drop data: URI images from the Markdown, keeping alt text. Default true."
}
},
"additionalProperties": false
}