Reliable web access for AI agents: smart HTTP, rotating proxies, and full-browser rendering.
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.
Give it a public URL and get the content back. Use it when only the content matters and not how it is fetched: it escalates from a direct request to a rotating proxy to a full browser only as far as the target forces, and returns the session that worked so the next call can replay it. On protected targets, or whenever HTTP 200 may still be a challenge or an incomplete page, pass validate.data.accept with text unique to the real content; auto makes bounded attempts and returns either validated content or a failure, and cannot guarantee a match. It owns its own retry settings, so there is no maxTries here, and timeout_ms is the budget for every attempt together rather than for one. What it cannot do is the reason to reach for another tool: a strict exit country and a pinned exit live on foura_proxy (auto can only avoid exits, through ignoreProxies, or escalate to a premium exit with exitClass); choosing which browser is presented to the target lives on foura_single and foura_proxy; a scripted browser session lives on foura_browser. A request that names any of those belongs there rather than here. One FourA API key authenticates every call, the result reports the credits it spent, which is the sum of the attempts it made, and a refusal by your own plan arrives as a plan_limit_ code with retryAfter rather than as a block by the target.
Public target URL. Private or reserved targets return `ssrf_blocked`. Use {ts} in the URL to insert the current Unix timestamp. Example: https://example.com/page.
Request body for non-GET methods. Strings sent as-is; objects auto-serialized to JSON.
HTTP method for the target request (default GET).
Custom HTTP headers as [name, value] tuples. Example: [["Accept", "application/json"], ["Authorization", "Bearer ..."]]
Post-fetch response validation. When the response fails these checks foura_auto returns an error envelope.
Exit class the call may use, as on foura_proxy. premium lets auto escalate to a premium exit once the standard pool cannot reach the page; it needs a plan with premium exits, and the result's exitClass says which class delivered. standard never escalates; omit for no preference.
Require proxy routing for every target request. Default true. Send false to allow direct HTTP when suitable.
Total time budget in ms for the whole operation. Every attempt must fit inside it. Default 120000, max 180000.
Exits to avoid - base36 proxy IDs (like "4DZ3VE") or proxy URLs. Use this to rotate away from an exit that was just blocked.
If true, response bodies of 50 KB or more are returned as a resource_link instead of inlined. Default false. Read the returned offloaded_resource_uri with resources/read.
Return reusable {proxy, cookies, userAgent} values for follow-up calls. Default true. Send false for a leaner response when you only need the content.
Follow up to N redirects for HTTP and proxy requests. Default 5; 0 means don't follow. Browser navigation handles redirects itself.
Give it a public URL and get the content back. Use it when only the content matters and not how it is fetched: it escalates from a direct request to a rotating proxy to a full browser only as far as the target forces, and returns the session that worked so the next call can replay it. On protected targets, or whenever HTTP 200 may still be a challenge or an incomplete page, pass validate.data.accept with text unique to the real content; auto makes bounded attempts and returns either validated content or a failure, and cannot guarantee a match. It owns its own retry settings, so there is no maxTries here, and timeout_ms is the budget for every attempt together rather than for one. What it cannot do is the reason to reach for another tool: a strict exit country and a pinned exit live on foura_proxy (auto can only avoid exits, through ignoreProxies, or escalate to a premium exit with exitClass); choosing which browser is presented to the target lives on foura_single and foura_proxy; a scripted browser session lives on foura_browser. A request that names any of those belongs there rather than here. One FourA API key authenticates every call, the result reports the credits it spent, which is the sum of the attempts it made, and a refusal by your own plan arrives as a plan_limit_ code with retryAfter rather than as a block by the target.
| Argument | Type | Description |
|---|---|---|
| url* | string | Public target URL. Private or reserved targets return `ssrf_blocked`. Use {ts} in the URL to insert the current Unix timestamp. Example: https://example.com/page. |
| data | any | Request body for non-GET methods. Strings sent as-is; objects auto-serialized to JSON. |
| method | string | HTTP method for the target request (default GET). |
| headers | array | Custom HTTP headers as [name, value] tuples. Example: [["Accept", "application/json"], ["Authorization", "Bearer ..."]] |
| validate | object | Post-fetch response validation. When the response fails these checks foura_auto returns an error envelope. |
| exitClass | string | Exit class the call may use, as on foura_proxy. premium lets auto escalate to a premium exit once the standard pool cannot reach the page; it needs a plan with premium exits, and the result's exitClass says which class delivered. standard never escalates; omit for no preference. |
| forceProxy | boolean | Require proxy routing for every target request. Default true. Send false to allow direct HTTP when suitable. |
| timeout_ms | integer | Total time budget in ms for the whole operation. Every attempt must fit inside it. Default 120000, max 180000. |
| ignoreProxies | array | Exits to avoid - base36 proxy IDs (like "4DZ3VE") or proxy URLs. Use this to rotate away from an exit that was just blocked. |
| offload_large | boolean | If true, response bodies of 50 KB or more are returned as a resource_link instead of inlined. Default false. Read the returned offloaded_resource_uri with resources/read. |
| returnSession | boolean | Return reusable {proxy, cookies, userAgent} values for follow-up calls. Default true. Send false for a leaner response when you only need the content. |
| followRedirects | integer | Follow up to N redirects for HTTP and proxy requests. Default 5; 0 means don't follow. Browser navigation handles redirects itself. |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public target URL. Private or reserved targets return `ssrf_blocked`. Use {ts} in the URL to insert the current Unix timestamp. Example: https://example.com/page."
},
"data": {
"anyOf": [
{
"type": "string"
},
{
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
],
"description": "Request body for non-GET methods. Strings sent as-is; objects auto-serialized to JSON."
},
"method": {
"type": "string",
"minLength": 1,
"description": "HTTP method for the target request (default GET)."
},
"headers": {
"type": "array",
"items": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 2,
"minItems": 2
},
"description": "Custom HTTP headers as [name, value] tuples. Example: [[\"Accept\", \"application/json\"], [\"Authorization\", \"Bearer ...\"]]"
},
"validate": {
"type": "object",
"properties": {
"data": {
"type": "object",
"properties": {
"fail": {
"type": "array",
"items": {
"type": "string"
},
"description": "Substrings the final body must not contain"
},
"accept": {
"type": "array",
"items": {
"type": "string"
},
"description": "Case-sensitive substrings the final body must contain. Use this on protected targets to distinguish the real page from a challenge page."
}
},
"description": "Body validation: pass when the body contains an expected substring (accept), fail when it contains a blocked one (fail)."
},
"status": {
"type": "object",
"properties": {
"fail": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
"description": "HTTP status codes to treat as failure"
},
"accept": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
"description": "HTTP status codes to treat as success"
}
},
"description": "Status-code validation: which HTTP status codes count as success (accept) or failure (fail)."
},
"headers": {
"type": "object",
"properties": {
"fail": {
"type": "object",
"description": "Case-insensitive header substring rules that reject the response when any name/value pair matches.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
},
"accept": {
"type": "object",
"description": "Case-insensitive header substring rules. The response passes when at least one name/value pair matches.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
}
},
"description": "Header validation: pass when an accepted header matches, fail when a blocklisted header matches."
}
},
"description": "Post-fetch response validation. When the response fails these checks foura_auto returns an error envelope."
},
"exitClass": {
"enum": [
"standard",
"premium"
],
"type": "string",
"description": "Exit class the call may use, as on foura_proxy. premium lets auto escalate to a premium exit once the standard pool cannot reach the page; it needs a plan with premium exits, and the result's exitClass says which class delivered. standard never escalates; omit for no preference."
},
"forceProxy": {
"type": "boolean",
"description": "Require proxy routing for every target request. Default true. Send false to allow direct HTTP when suitable."
},
"timeout_ms": {
"type": "integer",
"maximum": 180000,
"minimum": 5000,
"description": "Total time budget in ms for the whole operation. Every attempt must fit inside it. Default 120000, max 180000."
},
"ignoreProxies": {
"type": "array",
"items": {
"type": "string"
},
"description": "Exits to avoid - base36 proxy IDs (like \"4DZ3VE\") or proxy URLs. Use this to rotate away from an exit that was just blocked."
},
"offload_large": {
"type": "boolean",
"description": "If true, response bodies of 50 KB or more are returned as a resource_link instead of inlined. Default false. Read the returned offloaded_resource_uri with resources/read."
},
"returnSession": {
"type": "boolean",
"description": "Return reusable {proxy, cookies, userAgent} values for follow-up calls. Default true. Send false for a leaner response when you only need the content."
},
"followRedirects": {
"type": "integer",
"maximum": 20,
"minimum": 0,
"description": "Follow up to N redirects for HTTP and proxy requests. Default 5; 0 means don't follow. Browser navigation handles redirects itself."
}
}
}Load a public URL in a full browser session. JavaScript runs, the DOM renders, and cookies come back with the response. Use it for single-page apps, lazy-loaded content, or supported browser challenges. You can set your own headers, cookies and userAgent, and checkStatus or checkText turn a navigation that rendered the wrong page into a failure instead of returning it as content. For a protected page, call foura_proxy first and pass its returned proxy ID here to reuse that same exit, instead of starting a new selection here; with no proxy the session leaves from one fixed address. Set unblocker:false when you want the page exactly as it loads, challenge included. It is the most expensive of the four tools and the slowest, so prefer foura_single or foura_proxy whenever the content is already in the HTML. One FourA API key authenticates every call, the result reports the credits it spent, and a refusal by your own plan arrives as a plan_limit_ code, including plan_limit_browser_daily when the daily browser allowance is spent.
| Argument | Type | Description |
|---|---|---|
| url* | string | Public URL to load in a full browser session. Private or reserved targets return `ssrf_blocked`. Example: https://shop.example.com/product/123. |
| proxy | string | Optional proxy. Three forms: (1) URL `http://user:pass@host:port` or `socks5://host:port`; (2) base36 ID from foura_proxy (e.g. `4DZ3VE`) to reuse the same exit; (3) omit to use the default route. |
| cookies | array | Cookies to set before navigation: [{ name, value, domain? }] |
| headers | object | Custom HTTP headers as a key-value object rather than [name, value] tuples. Example: {"Referer": "https://google.com/"} |
Route an HTTP request through rotating proxies, retrying on another exit until one delivers. Use it when foura_single is blocked, and whenever the exit itself matters: this is the only tool that takes a strict exit-country allowlist (exitCountries, which never falls back to another country), presents a named browser family per attempt, excludes exits you already know are dead (ignoreProxies), and may escalate to a premium exit (exitClass, an allowance rather than an instruction). maxTries bounds how many exits are tried and timeout_ms bounds the whole rotation, so a short timeout can end it before maxTries is reached; protected targets often need 25 to 30. validate decides what counts as delivered, and an attempt it rejects is retried on the next exit. The response returns the id of the exit that succeeded: pass that returned id to foura_single.proxy or foura_browser.proxy to send the next request from the same exit. A failed rotation returns attemptReport, which separates exits that never answered from exits a bot check refused from pages your own rule threw away. Use foura_browser when the page needs JavaScript. Rotation costs several times a single request. One FourA API key authenticates every call, the result reports the credits it spent, and a refusal by your own plan arrives as a plan_limit_ code with retryAfter rather than as a block by the target.
| Argument | Type | Description |
|---|---|---|
| request* | object | The inner HTTP request to send through each proxy attempt. Validation rules here determine when a proxy is treated as failed and retried. |
| maxTries | integer | Maximum rotation attempts before giving up (default 5, max 90). Difficult protected targets may need 25-30. Use exitCountries for country scope. |
| exitClass | string |
Send one HTTP request and return the response. Use it for static pages, JSON APIs, and server-rendered HTML, with your own headers, body and cookies. Set browser, os, or version when a target refuses the default Chrome. Pass a proxy id returned by foura_proxy to leave from that same exit. validate decides what counts as success, so a response it rejects comes back as a failure instead of as content; the timeouts nest, with timeout_ms bounding the whole request and the connect, accept and server_response ones bounding stages inside it. Switch to foura_proxy when the response is blocked or the exit country matters, and to foura_browser when the page needs JavaScript. One FourA API key authenticates every call, the result reports the credits it spent, and a refusal by your own plan arrives as a plan_limit_ code with retryAfter rather than as a block by the target.
| Argument | Type | Description |
|---|---|---|
| os | string | Operating system to present: Windows, macOS, Android, or iOS. A family name accepts any of its versions. |
| url* | string | Public target URL. Private or reserved targets return `ssrf_blocked`. Use {ts} in the URL to insert the current Unix timestamp. Example: https://api.example.com/v1/users. |
| data | any | Request body. Strings sent as-is; objects auto-serialized to JSON. Example: {"query": "hello"} for POST APIs. |
| proxy | string | Optional proxy. Two forms: (1) URL `http://host:port` or `socks5://host:port`; (2) base36 ID from foura_proxy (e.g. `4DZ3VE`) to reuse the same exit. For rotation, use foura_proxy. |
| checkText | string | Validate the rendered HTML once navigation completes. This is a substring check, not a waiter, and it doesn't poll. A missing substring returns an error envelope. Example: "add to cart" for a product page. |
| unblocker | boolean | Handle supported anti-bot or captcha challenges during navigation. Default true. Set false to return the page exactly as it loads, including any challenge page. |
| userAgent | string | Override the browser's User-Agent string |
| timeout_ms | integer | Page load timeout in ms (default 30000, max 120000) |
| checkStatus | integer | Expected HTTP status code. A different status returns an error envelope carrying the actual value. Example: 200 for a product page. |
| offload_large | boolean | If true, response bodies of 50 KB or more are returned as a resource_link instead of inlined. Default false. Read the returned offloaded_resource_uri with resources/read. |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public URL to load in a full browser session. Private or reserved targets return `ssrf_blocked`. Example: https://shop.example.com/product/123."
},
"proxy": {
"type": "string",
"description": "Optional proxy. Three forms: (1) URL `http://user:pass@host:port` or `socks5://host:port`; (2) base36 ID from foura_proxy (e.g. `4DZ3VE`) to reuse the same exit; (3) omit to use the default route."
},
"cookies": {
"type": "array",
"items": {
"type": "object",
"required": [
"name",
"value"
],
"properties": {
"name": {
"type": "string",
"description": "Cookie name."
},
"value": {
"type": "string",
"description": "Cookie value."
},
"domain": {
"type": "string",
"description": "Cookie domain (e.g. .example.com). Omit to scope it to the navigated URL's host."
}
}
},
"description": "Cookies to set before navigation: [{ name, value, domain? }]"
},
"headers": {
"type": "object",
"description": "Custom HTTP headers as a key-value object rather than [name, value] tuples. Example: {\"Referer\": \"https://google.com/\"}",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
},
"checkText": {
"type": "string",
"description": "Validate the rendered HTML once navigation completes. This is a substring check, not a waiter, and it doesn't poll. A missing substring returns an error envelope. Example: \"add to cart\" for a product page."
},
"unblocker": {
"type": "boolean",
"description": "Handle supported anti-bot or captcha challenges during navigation. Default true. Set false to return the page exactly as it loads, including any challenge page."
},
"userAgent": {
"type": "string",
"description": "Override the browser's User-Agent string"
},
"timeout_ms": {
"type": "integer",
"maximum": 120000,
"minimum": 0,
"description": "Page load timeout in ms (default 30000, max 120000)"
},
"checkStatus": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Expected HTTP status code. A different status returns an error envelope carrying the actual value. Example: 200 for a product page."
},
"offload_large": {
"type": "boolean",
"description": "If true, response bodies of 50 KB or more are returned as a resource_link instead of inlined. Default false. Read the returned offloaded_resource_uri with resources/read."
}
}
}| Allow escalation to a premium exit for a target the standard pool cannot deliver. An allowance, not an instruction: the pool still races and usually wins, and the response reports which class served. `standard` forbids escalation. Without premium exits in the plan the call is refused with code plan_limit_premium. |
| timeout_ms | integer | Overall timeout across all rotation attempts in ms (default 45000, max 120000). Must be positive. |
| exitCountries | array | Optional target-visible proxy countries as two-letter provider codes, for example ["CZ", "GB"]. Use codes supplied by the user or target requirements. When geography matters, do not guess codes or substitute unscoped rotation. Values are trimmed, uppercased, and deduplicated. Unknown exits are excluded and the request never falls back to another country. |
| ignoreProxies | array | Encoded proxy IDs (base36 strings like "4DZ3VE") or proxy URLs to exclude from rotation. |
| offload_large | boolean | If true, response bodies of 50 KB or more are returned as a resource_link instead of inlined. Default false. Read the returned offloaded_resource_uri with resources/read. |
{
"type": "object",
"required": [
"request"
],
"properties": {
"request": {
"type": "object",
"required": [
"method",
"url"
],
"properties": {
"os": {
"type": "string",
"description": "Operating system to present: Windows, macOS, Android, or iOS. A family name accepts any of its versions."
},
"url": {
"type": "string",
"format": "uri",
"description": "Public target URL. Private or reserved targets return `ssrf_blocked`. Use {ts} in the URL to insert the current Unix timestamp. Example: https://shop.example.com/pricing."
},
"data": {
"anyOf": [
{
"type": "string"
},
{
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
],
"description": "Request body."
},
"method": {
"type": "string",
"minLength": 1,
"description": "HTTP method (GET, POST, PUT, PATCH, DELETE, HEAD, OPTIONS, or any WebDAV verb)"
},
"browser": {
"type": "string",
"description": "Browser to present: Chrome, Edge, Safari, Firefox, or Tor. Omit every profile field and the request presents the latest Google Chrome."
},
"headers": {
"type": "array",
"items": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 2,
"minItems": 2
},
"description": "Custom HTTP headers as [name, value] tuples. Example: [[\"Accept\", \"application/json\"]]"
},
"profile": {
"type": "string",
"description": "Exact profile id from the public catalogue at https://api.foura.ai/api/profiles. Use browser/os/version when you do not have an id."
},
"version": {
"type": "string",
"description": "Browser version to present, as listed in the catalogue. The newest match wins when several fit. An impossible combination returns an error listing what is available; no other browser is substituted."
},
"validate": {
"type": "object",
"properties": {
"data": {
"type": "object",
"properties": {
"fail": {
"type": "array",
"items": {
"type": "string"
},
"description": "Substrings that, if present in the body, mark the response as failed."
},
"accept": {
"type": "array",
"items": {
"type": "string"
},
"description": "Substrings the response body must contain to pass."
}
},
"description": "Body validation: pass when the body contains an expected substring (accept), fail when it contains a blocked one (fail)."
},
"status": {
"type": "object",
"properties": {
"fail": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
"description": "HTTP status codes to treat as failure"
},
"accept": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
"description": "HTTP status codes to treat as success"
}
},
"description": "Status-code validation: which HTTP status codes count as success (accept) or failure (fail)."
},
"headers": {
"type": "object",
"properties": {
"fail": {
"type": "object",
"description": "Case-insensitive header substring rules that reject the response when any name/value pair matches.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
},
"accept": {
"type": "object",
"description": "Case-insensitive header substring rules. The response passes when at least one name/value pair matches across the redirect chain.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
}
},
"description": "Header validation: pass when an accepted header matches, fail when a blocklisted header matches."
}
},
"description": "Per-attempt response validation. A proxy attempt that fails these checks is treated as failed and the next proxy is tried."
},
"unblocker": {
"type": "boolean",
"description": "Send a full browser header set, including User-Agent and Sec-Ch-Ua. Default true. Set false for a plain HTTP request; profile selection needs it on and errors when it is off."
},
"timeout_ms": {
"type": "integer",
"maximum": 120000,
"minimum": 0,
"description": "Per-attempt timeout in ms"
},
"tryJsonData": {
"type": "boolean",
"description": "If true, attempt JSON.parse on the response body; on success `data` is the parsed value, otherwise it stays the original string. Omit to keep the body as-is."
},
"returnBuffer": {
"type": "boolean",
"description": "Return raw bytes as a serialized Buffer JSON shape ({type:\"Buffer\", data:[byte, ...]}) instead of a decoded string. Use for binary responses (images, protobuf)."
},
"followRedirects": {
"type": "integer",
"maximum": 20,
"minimum": 0,
"description": "Max number of redirects to follow (0-20). Omit to disable redirect following."
},
"accept_timeout_ms": {
"type": "integer",
"maximum": 120000,
"minimum": 0,
"description": "Timeout in ms to receive the first response byte after the request is sent (0-120000). Omit for the default."
},
"connect_timeout_ms": {
"type": "integer",
"maximum": 120000,
"minimum": 0,
"description": "Timeout in ms for establishing the connection to the target through the proxy (0-120000). Omit for the default."
},
"dns_cache_timeout_sec": {
"type": "integer",
"maximum": 240,
"minimum": 0,
"description": "How long (seconds) to cache the target's resolved DNS (0-240). Omit for the default."
},
"server_response_timeout_ms": {
"type": "integer",
"maximum": 120000,
"minimum": 0,
"description": "Timeout in ms for the server to send the complete response (0-120000). Omit for the default."
}
},
"description": "The inner HTTP request to send through each proxy attempt. Validation rules here determine when a proxy is treated as failed and retried."
},
"maxTries": {
"type": "integer",
"maximum": 90,
"minimum": 1,
"description": "Maximum rotation attempts before giving up (default 5, max 90). Difficult protected targets may need 25-30. Use exitCountries for country scope."
},
"exitClass": {
"enum": [
"standard",
"premium"
],
"type": "string",
"description": "Allow escalation to a premium exit for a target the standard pool cannot deliver. An allowance, not an instruction: the pool still races and usually wins, and the response reports which class served. `standard` forbids escalation. Without premium exits in the plan the call is refused with code plan_limit_premium."
},
"timeout_ms": {
"type": "integer",
"maximum": 120000,
"description": "Overall timeout across all rotation attempts in ms (default 45000, max 120000). Must be positive.",
"exclusiveMinimum": 0
},
"exitCountries": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[A-Z]{2}$"
},
"minItems": 1,
"description": "Optional target-visible proxy countries as two-letter provider codes, for example [\"CZ\", \"GB\"]. Use codes supplied by the user or target requirements. When geography matters, do not guess codes or substitute unscoped rotation. Values are trimmed, uppercased, and deduplicated. Unknown exits are excluded and the request never falls back to another country."
},
"ignoreProxies": {
"type": "array",
"items": {
"type": "string"
},
"description": "Encoded proxy IDs (base36 strings like \"4DZ3VE\") or proxy URLs to exclude from rotation."
},
"offload_large": {
"type": "boolean",
"description": "If true, response bodies of 50 KB or more are returned as a resource_link instead of inlined. Default false. Read the returned offloaded_resource_uri with resources/read."
}
}
}| method* |
| string |
| HTTP method (GET, POST, PUT, PATCH, DELETE, HEAD, OPTIONS, or any WebDAV verb like PROPFIND/MKCOL) |
| browser | string | Browser to present: Chrome, Edge, Safari, Firefox, or Tor. Omit every profile field and the request presents the latest Google Chrome. |
| headers | array | Custom HTTP headers as [name, value] tuples. Example: [["Accept", "application/json"], ["Referer", "https://google.com/"]] |
| profile | string | Exact profile id from the public catalogue at https://api.foura.ai/api/profiles. Use browser/os/version when you do not have an id. |
| version | string | Browser version to present, as listed in the catalogue. The newest match wins when several fit. An impossible combination returns an error listing what is available; no other browser is substituted. |
| validate | object | Post-fetch response validation. When the response fails these checks the tool returns an error envelope. |
| unblocker | boolean | Send a full browser header set, including User-Agent and Sec-Ch-Ua. Default true. Set false for a plain HTTP request; profile selection needs it on and errors when it is off. |
| timeout_ms | integer | Overall request timeout in ms (max 120000, default 15000) |
| tryJsonData | boolean | If true, attempt JSON.parse on the response body. On success, `data` is the parsed value (typically object or array). On parse failure, `data` silently stays as the original string - no error, no warning. Set false (or omit) when you need to detect parse failures explicitly. |
| returnBuffer | boolean | Return raw bytes as a serialized Buffer JSON shape (`{type:"Buffer", data:[byte, ...]}`, bytes 0-255) instead of decoded string. Use for binary responses (images, protobuf). Reconstruct: `Buffer.from(data.data)` in Node, `new Uint8Array(data.data)` elsewhere. |
| offload_large | boolean | If true, response bodies of 50 KB or more are returned as a resource_link instead of inlined. Default false. Read the returned offloaded_resource_uri with resources/read. |
| followRedirects | integer | Max number of redirects to follow (0-20). Omit to disable redirect following. |
| accept_timeout_ms | integer | Timeout in ms to receive the first response byte after the request is sent (0-120000). Omit for the default. |
| connect_timeout_ms | integer | Timeout in ms for establishing the TCP/TLS connection (0-120000). Omit to use the default. |
| dns_cache_timeout_sec | integer | How long (seconds) to cache the target's resolved DNS (0-240). Omit for the default. |
| server_response_timeout_ms | integer | Timeout in ms for the server to send the complete response (0-120000). Omit for the default. |
{
"type": "object",
"required": [
"method",
"url"
],
"properties": {
"os": {
"type": "string",
"description": "Operating system to present: Windows, macOS, Android, or iOS. A family name accepts any of its versions."
},
"url": {
"type": "string",
"format": "uri",
"description": "Public target URL. Private or reserved targets return `ssrf_blocked`. Use {ts} in the URL to insert the current Unix timestamp. Example: https://api.example.com/v1/users."
},
"data": {
"anyOf": [
{
"type": "string"
},
{
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
],
"description": "Request body. Strings sent as-is; objects auto-serialized to JSON. Example: {\"query\": \"hello\"} for POST APIs."
},
"proxy": {
"type": "string",
"description": "Optional proxy. Two forms: (1) URL `http://host:port` or `socks5://host:port`; (2) base36 ID from foura_proxy (e.g. `4DZ3VE`) to reuse the same exit. For rotation, use foura_proxy."
},
"method": {
"type": "string",
"minLength": 1,
"description": "HTTP method (GET, POST, PUT, PATCH, DELETE, HEAD, OPTIONS, or any WebDAV verb like PROPFIND/MKCOL)"
},
"browser": {
"type": "string",
"description": "Browser to present: Chrome, Edge, Safari, Firefox, or Tor. Omit every profile field and the request presents the latest Google Chrome."
},
"headers": {
"type": "array",
"items": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 2,
"minItems": 2
},
"description": "Custom HTTP headers as [name, value] tuples. Example: [[\"Accept\", \"application/json\"], [\"Referer\", \"https://google.com/\"]]"
},
"profile": {
"type": "string",
"description": "Exact profile id from the public catalogue at https://api.foura.ai/api/profiles. Use browser/os/version when you do not have an id."
},
"version": {
"type": "string",
"description": "Browser version to present, as listed in the catalogue. The newest match wins when several fit. An impossible combination returns an error listing what is available; no other browser is substituted."
},
"validate": {
"type": "object",
"properties": {
"data": {
"type": "object",
"properties": {
"fail": {
"type": "array",
"items": {
"type": "string"
},
"description": "Substrings the response body must not contain"
},
"accept": {
"type": "array",
"items": {
"type": "string"
},
"description": "Substrings the response body must contain"
}
},
"description": "Body validation: pass when the body contains an expected substring (accept), fail when it contains a blocked one (fail)."
},
"status": {
"type": "object",
"properties": {
"fail": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
"description": "HTTP status codes to treat as failure"
},
"accept": {
"type": "array",
"items": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
"description": "HTTP status codes to treat as success"
}
},
"description": "Status-code validation: which HTTP status codes count as success (accept) or failure (fail)."
},
"headers": {
"type": "object",
"properties": {
"fail": {
"type": "object",
"description": "Case-insensitive header substring rules that reject the response when any name/value pair matches.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
},
"accept": {
"type": "object",
"description": "Case-insensitive header substring rules. The response passes when at least one name/value pair matches across the redirect chain.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
}
},
"description": "Header validation: pass when an accepted header matches, fail when a blocklisted header matches."
}
},
"description": "Post-fetch response validation. When the response fails these checks the tool returns an error envelope."
},
"unblocker": {
"type": "boolean",
"description": "Send a full browser header set, including User-Agent and Sec-Ch-Ua. Default true. Set false for a plain HTTP request; profile selection needs it on and errors when it is off."
},
"timeout_ms": {
"type": "integer",
"maximum": 120000,
"minimum": 0,
"description": "Overall request timeout in ms (max 120000, default 15000)"
},
"tryJsonData": {
"type": "boolean",
"description": "If true, attempt JSON.parse on the response body. On success, `data` is the parsed value (typically object or array). On parse failure, `data` silently stays as the original string - no error, no warning. Set false (or omit) when you need to detect parse failures explicitly."
},
"returnBuffer": {
"type": "boolean",
"description": "Return raw bytes as a serialized Buffer JSON shape (`{type:\"Buffer\", data:[byte, ...]}`, bytes 0-255) instead of decoded string. Use for binary responses (images, protobuf). Reconstruct: `Buffer.from(data.data)` in Node, `new Uint8Array(data.data)` elsewhere."
},
"offload_large": {
"type": "boolean",
"description": "If true, response bodies of 50 KB or more are returned as a resource_link instead of inlined. Default false. Read the returned offloaded_resource_uri with resources/read."
},
"followRedirects": {
"type": "integer",
"maximum": 20,
"minimum": 0,
"description": "Max number of redirects to follow (0-20). Omit to disable redirect following."
},
"accept_timeout_ms": {
"type": "integer",
"maximum": 120000,
"minimum": 0,
"description": "Timeout in ms to receive the first response byte after the request is sent (0-120000). Omit for the default."
},
"connect_timeout_ms": {
"type": "integer",
"maximum": 120000,
"minimum": 0,
"description": "Timeout in ms for establishing the TCP/TLS connection (0-120000). Omit to use the default."
},
"dns_cache_timeout_sec": {
"type": "integer",
"maximum": 240,
"minimum": 0,
"description": "How long (seconds) to cache the target's resolved DNS (0-240). Omit for the default."
},
"server_response_timeout_ms": {
"type": "integer",
"maximum": 120000,
"minimum": 0,
"description": "Timeout in ms for the server to send the complete response (0-120000). Omit for the default."
}
}
}