nexus-browser

Overview Schema Source Related Servers Discussions Admin

browser_export

Read-onlyIdempotent

Extract the main readable content from a browser page, stripping menus, ads, banners, sidebars, and footers. Export it as markdown, text, or cleaned HTML for analysis, summaries, or documentation.

Instructions

Exports the MAIN content of the page (article, documentation, post) without menus, ads, cookie banners, sidebars or footers: the tool for READING a page (browser_content(mode="text"/"html") returns everything).

format: "markdown" (default: headings, paragraphs, lists, absolute links, tables, code blocks), "text" (structured plain text) or "html" (cleaned HTML: structural tags only, no attributes or scripts). selector (CSS) or locator (like browser_find, strict): export one area only. max_chars bounds content (truncation reported: truncated, total_chars). Response: content, metadata (title, author, published, modified, lang, site_name, description, canonical), root (chosen root: article, main, scored, body, selector, locator), stats. Never the value of a form field.

Input Schema

Name	Required	Description	Default
`format`	No		markdown
`tab_id`	Yes	Your tab's id (from browser_new_tab, or a tab adopted with browser_adopt_tab).
`locator`	No
`selector`	No
`max_chars`	No

Output Schema

Name	Required	Description
`data`	Yes
`status`	Yes
`warning`	No	Emergency stop hotkey not held, or similar notice
`untrusted_note`	No	Page text that looks like instructions aimed at an AI

Schema Changelog

Changes observed during successful MCP inspections.

Changed10 schema fields changedv2.31.6Oct 29, 2026

addedOutput schema / $defs

Added value: +{
+  "ExportRoot": {
+    "additionalProperties": true,
+    "properties": {
+      "blocks": {
+        "type": "integer"
+      },
+      "id": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "method": {
+        "type": "string"
+      },
+      "tag": {
+        "type": "string"
+      }
+    },
+    "title": "ExportRoot",
+    "type": "object"
+  },
+  "PageDialog": {
+    "additionalProperties": true,
+    "description": "Dialog opened by the page (never accepted by the agent: browser_handle_dialog).",
+    "properties": {
+      "defaultPrompt": {
+        "type": "string"
+      },
+      "message": {
+        "type": "string"
+      },
+      "tabId": {
+        "type": "integer"
+      },
+      "type": {
+        "type": "string"
+      },
+      "url": {
+        "type": "string"
+      }
+    },
+    "title": "PageDialog",
+    "type": "object"
+  },
+  "PageExport": {
+    "additionalProperties": true,
+    "properties": {
+      "chars": {
+        "type": "integer"
+      },
+      "content": {
+        "type": "string"
+      },
+      "dialog": {
+        "$ref": "#/$defs/PageDialog"
+      },
+      "dialogOpened": {
+        "type": "boolean"
+      },
+      "format": {
+        "type": "string"
+      },
+      "message": {
+        "type": "string"
+      },
+      "metadata": {
+        "additionalProperties": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "type": "object"
+      },
+      "pendingDialogs": {
+        "items": {
+          "$ref": "#/$defs/PageDialog"
+        },
+        "type": "array"
+      },
+      "root": {
+        "$ref": "#/$defs/ExportRoot"
+      },
+      "stats": {
+        "additionalProperties": {
+          "type": "integer"
+        },
+        "type": "object"
+      },
+      "title": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "total_chars": {
+        "type": "integer"
+      },
+      "truncated": {
+        "type": "boolean"
+      },
+      "url": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      }
+    },
+    "title": "PageExport",
+    "type": "object"
+  }
+}

addedOutput schema / additionalProperties
```
Added value: +true
```

addedOutput schema / description

Added value: +"Main content of the page."

addedOutput schema / properties / data

Added value: +{
+  "$ref": "#/$defs/PageExport"
+}

removedOutput schema / properties / result

Removed value: -{
-  "title": "Result",
-  "type": "string"
-}

addedOutput schema / properties / status

Added value: +{
+  "const": "success",
+  "type": "string"
+}

addedOutput schema / properties / untrusted_note

Added value: +{
+  "description": "Page text that looks like instructions aimed at an AI",
+  "type": "string"
+}

addedOutput schema / properties / warning

Added value: +{
+  "description": "Emergency stop hotkey not held, or similar notice",
+  "type": "string"
+}

changedOutput schema / required

Previous value: -[
-  "result"
-]New value: +[
+  "status",
+  "data"
+]

changedOutput schema / title

Previous value: -"browser_exportOutput"New value: +"ExportAnswer"

First observedv0.1.0Oct 26, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the bar is lower. The description still adds real behavior: truncation is reported via truncated/total_chars, the root-selection heuristic (article, main, scored, body, selector, locator), and the notable caveat that form-field values are never returned. Some of the response-field listing duplicates the output schema, which keeps it from a 5.

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?

Purpose and the sibling contrast are front-loaded in the first sentence, and the remaining spec-style fragments are dense rather than padded. The enumerated response fields (content, metadata, root, stats) are the least essential part since an output schema exists.

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

Completeness5/5

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

For a 5-parameter read tool with an output schema and rich annotations, nothing an agent needs is missing: format choices, area narrowing, size bounding, truncation semantics, root selection and the form-field exclusion are all covered.

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

Parameters4/5

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

Schema coverage is only 20% (just tab_id), so the description must carry the load and largely does: it spells out the three format values, distinguishes selector (CSS) from locator (like browser_find, strict), and explains that max_chars bounds content with reported truncation. The locator object's internal structure is left only as a reference to browser_find.

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?

States a specific verb (exports) and resource (MAIN page content), and immediately scopes it by excluding menus, ads, cookie banners, sidebars and footers. It also names the sibling it differs from (browser_content returning everything), so an agent can pick between them without opening a schema.

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?

"the tool for READING a page" plus the explicit contrast with browser_content(mode="text"/"html") gives a clear selection rule, and the selector/locator clause explains when to narrow to one area. It stops short of explicit exclusions (e.g. when to prefer browser_pdf, browser_axtree or browser_screenshot instead).

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

Deploy Server