Skip to main content
Glama
NexBrowser MCP Server

NexBrowser MCP Server

Official
by nex-browser

nex_browser_take_screenshot

Capture viewport, element, or clipped browser screenshots and return pixel-to-CSS mapping for accurate click coordinates.

Instructions

Capture the viewport, one target, or a viewport clip (target, clip and fullPage=true are mutually exclusive). The returned origin and pixelsPerCssPixel map image pixels to nex_browser_mouse_click_xy coordinates. Page CAPTCHA: default to nex_captcha_product_schema, collect real page inputs with permitted tools, then use free nex_captcha_detect with productCode/adapter. Confirm application capability before NexCaptcha buy/query and apply the result in the original page. nex_browser_captcha_prepare is optional; never bypass browser permissions.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "nex_browser_take_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
clipNo
typeNo
scaleNo
pageIdNoDefaults to the active page
targetNoSnapshot ref (e12) or unique CSS selector
qualityNo
filenameNo
fullPageNo
sessionIdNoDefaults to the active session

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv2026.10.24
    • addedInput schema / properties / clip
      Added value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "height": {
      +      "exclusiveMinimum": 0,
      +      "type": "number"
      +    },
      +    "width": {
      +      "exclusiveMinimum": 0,
      +      "type": "number"
      +    },
      +    "x": {
      +      "minimum": 0,
      +      "type": "number"
      +    },
      +    "y": {
      +      "minimum": 0,
      +      "type": "number"
      +    }
      +  },
      +  "required": [
      +    "x",
      +    "y",
      +    "width",
      +    "height"
      +  ],
      +  "type": "object"
      +}
    • changedInput schema / properties / pageId / description
      Previous value: -"Stable page ID; defaults to the session active page"New value: +"Defaults to the active page"
    • addedInput schema / properties / scale
      Added value: +{
      +  "enum": [
      +    "css",
      +    "device"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / sessionId / description
      Previous value: -"Optional session ID; defaults to this MCP client active session"New value: +"Defaults to the active session"
    • addedInput schema / properties / target
      Added value: +{
      +  "description": "Snapshot ref (e12) or unique CSS selector",
      +  "type": "string"
      +}
  2. Addedv2026.8.14

TDQS

A3.8/5.0
Behavior3/5

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

With no annotations, the description must carry the full behavioral burden. It does disclose the return payload semantics (origin and pixelsPerCssPixel for pixel-to-coordinate mapping), which is genuinely useful, but it never states defaults (type, scale), whether output is inline data or a file when filename is supplied, or explicitly that the tool is read-only with no page side effects.

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

Conciseness3/5

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

The first two sentences are tight, front-loaded, and high value. The remaining three sentences pivot to a general CAPTCHA handling workflow (product schema, detect, buy/query, captcha_prepare) that is largely orthogonal to taking a screenshot, diluting an otherwise excellent definition.

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 9-parameter, zero-annotation, no-output-schema tool it covers the critical selection rules and return-value meaning, which is most of what an agent needs. It still leaves defaults (what a bare call captures, default scale/format) and file-output behavior unexplained.

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 coverage is only 33% (only pageId and target are documented inline), so the description adds real value by explaining target versus clip versus fullPage exclusivity. However, 6 of 9 parameters — type, scale, quality, filename, sessionId, and the clip sub-fields — receive no semantic explanation anywhere beyond bare types and enums.

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 first sentence names a specific verb and enumerates the three capture modes (viewport, single target, viewport clip), so an agent knows exactly what will be produced. It also names the coordinate consumer (nex_browser_mouse_click_xy), which distinguishes this from generic snapshot tools like nex_browser_snapshot.

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 declares that target, clip and fullPage=true are mutually exclusive, which is the key selection rule an agent needs. It does not give a clear when-not-to-use (e.g. use nex_browser_snapshot for DOM/accessibility refs instead), and the trailing CAPTCHA workflow block is guidance for a different task rather than for choosing this tool.

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

Deploy Server

Other Tools