AginxBrowser

Overview Schema Source Related Servers Discussions Admin

fetch

Read-only

Fetch any web page and return clean markdown, HTML, or text. Handles JavaScript-rendered and Cloudflare-protected sites for reliable reading.

Instructions

Fetch a webpage and return clean markdown/html/text. Use whenever the agent needs to READ any web page - blogs, docs, articles, JS-rendered SPAs, Cloudflare-protected sites. Static pages are served over plain HTTP (~100ms tier:"http"); pages that need JS get the full browser (tier:"browser"). render_tier selects auto (default) / http (pure HTTP, refuses the upgrade) / browser (always the JS browser).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`url`	Yes	The URL to fetch
`format`	No	Output format: "markdown", "html", or "text" (default: markdown)	markdown
`sanitize`	No	Strip prompt-injection payloads from the text output (default true): zero-width/steganographic characters, instruction-shaped lines ("ignore previous instructions", chat markup tokens, CJK variants), and text hidden via opacity:0 / tiny fonts. A `sanitize_report` field counts what was removed — stripping is observable, never silent. Set false for raw output.
`selector`	No	CSS selector to extract specific content
`max_chars`	No	Maximum characters to return (default: 50000)
`use_proxy`	No	Route through proxy (for blocked foreign sites)
`wait_secs`	No	Seconds to wait for JS rendering
`js_extract`	No	JS expression to extract from the page after rendering
`capture_xhr`	No	Capture script-initiated API responses: a list of URL substrings (e.g. ["/api/"]) whose matching fetch/XHR bodies come back in an `xhr` array; an empty list captures every XHR/Fetch. Forces browser rendering (script-initiated requests only exist after JS runs).
`render_tier`	No	Rendering strategy: "auto" (default), "http", or "browser"	auto
`tls_fingerprint`	No	TLS fingerprint override (stealth mode only): "chrome145", "firefox133", etc.
`auto_bypass_challenge`	No	Auto-detect and bypass Cloudflare Turnstile challenges (default: true)

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.5.11Sep 26, 2026

changedInput schema / $defs / RenderTier / oneOf

Previous value: -[
-  {
-    "const": "auto",
-    "description": "HTTP-direct first, fall back to diting browser. (default)",
-    "type": "string"
-  },
-  {
-    "const": "http",
-    "description": "Pure HTTP, no V8/JS. Fastest; misses JS-rendered content.",
-    "type": "string"
-  },
-  {
-    "const": "obscura",
-    "description": "Always use the diting browser (current behaviour pre-tiering).\n\"browser\" is accepted as an alias — agents guess it before \"obscura\".",
-    "type": "string"
-  }
-]New value: +[
+  {
+    "const": "auto",
+    "description": "HTTP-direct first, fall back to diting browser. (default)",
+    "type": "string"
+  },
+  {
+    "const": "http",
+    "description": "Pure HTTP, no V8/JS. Fastest; misses JS-rendered content.",
+    "type": "string"
+  },
+  {
+    "const": "browser",
+    "description": "Always use the diting browser (current behaviour pre-tiering).\nWire name is \"browser\". \"obscura\" is still accepted and not advertised.",
+    "type": "string"
+  }
+]

changedInput schema / properties / render_tier / description

Previous value: -"Rendering strategy: \"auto\" (default), \"http\", or \"obscura\""New value: +"Rendering strategy: \"auto\" (default), \"http\", or \"browser\""

Changed1 schema field changedv0.5.1Sep 20, 2026
- removedInput schema / title
```
Removed value: -"FetchParams"
```

Changed3 schema fields changedv0.3.3-rc1Sep 9, 2026

changedInput schema / $defs / RenderTier / oneOf

Previous value: -[
-  {
-    "const": "auto",
-    "description": "HTTP-direct first, fall back to diting browser. (default)",
-    "type": "string"
-  },
-  {
-    "const": "http",
-    "description": "Pure HTTP, no V8/JS. Fastest; misses JS-rendered content.",
-    "type": "string"
-  },
-  {
-    "const": "obscura",
-    "description": "Always use the diting browser (current behaviour pre-tiering).",
-    "type": "string"
-  }
-]New value: +[
+  {
+    "const": "auto",
+    "description": "HTTP-direct first, fall back to diting browser. (default)",
+    "type": "string"
+  },
+  {
+    "const": "http",
+    "description": "Pure HTTP, no V8/JS. Fastest; misses JS-rendered content.",
+    "type": "string"
+  },
+  {
+    "const": "obscura",
+    "description": "Always use the diting browser (current behaviour pre-tiering).\n\"browser\" is accepted as an alias — agents guess it before \"obscura\".",
+    "type": "string"
+  }
+]

addedInput schema / properties / capture_xhr

Added value: +{
+  "default": null,
+  "description": "Capture script-initiated API responses: a list of URL substrings\n(e.g. [\"/api/\"]) whose matching fetch/XHR bodies come back in an\n`xhr` array; an empty list captures every XHR/Fetch. Forces browser\nrendering (script-initiated requests only exist after JS runs).",
+  "items": {
+    "type": "string"
+  },
+  "type": [
+    "array",
+    "null"
+  ]
+}

addedInput schema / properties / sanitize

Added value: +{
+  "default": true,
+  "description": "Strip prompt-injection payloads from the text output (default true):\nzero-width/steganographic characters, instruction-shaped lines\n(\"ignore previous instructions\", chat markup tokens, CJK variants),\nand text hidden via opacity:0 / tiny fonts. A `sanitize_report`\nfield counts what was removed — stripping is observable, never\nsilent. Set false for raw output.",
+  "type": "boolean"
+}

First observedSep 6, 2026

TDQS

A4.1/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint annotation, the description discloses meaningful behavior: static pages use plain HTTP, JS pages use a full browser, and render_tier controls auto/http/browser with the nuance that http 'refuses the upgrade.' This gives the agent a real sense of how the tool behaves at runtime, though some details like sanitization are left to the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, front-loaded with the core purpose, and each sentence adds useful information. The rendering-tier explanation is a bit dense and contains awkward formatting, but there is no wasted prose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 12 parameters and no output schema, the description covers the essential invocation context: what it returns, when to use it, and how rendering tiers work. It does not enumerate every parameter, but the schema provides that detail, so the description is sufficiently complete for an agent to select and call the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds a little extra color around render_tier (e.g., 'refuses the upgrade') but mostly restates what the schema already documents. It does not materially improve understanding of the other 11 parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Fetch a webpage and return clean markdown/html/text.' It clearly positions the tool as the read-only web-fetching option among siblings like download, search, and session_navigate, and the mention of JS-rendered SPAs and Cloudflare-protected sites further distinguishes its scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says 'Use whenever the agent needs to READ any web page' and gives concrete examples (blogs, docs, articles, JS-rendered SPAs, Cloudflare-protected sites). It does not explicitly name alternative tools or exclusion cases, but the context is clear enough for an agent to select this tool over session-based or download siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

fetch

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools