Skip to main content
Glama
NexBrowser MCP Server

NexBrowser MCP Server

Official
by nex-browser

nex_browser_create

Create NexBrowser environments in the desktop app's active workspace, with per-window fingerprints and optional overrides for proxy, accounts, plugins, groups, and startup URL.

Instructions

Create NexBrowser environments in the desktop app's active workspace. Every unset field falls back to the desktop create-window defaults (fingerprint, preferences, layout, startup page), and each created window gets its own generated fingerprint, so pass only the fields that must differ.

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_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoWindow title; a batch of more than one appends -01, -02 to this name
countNoHow many to create
remarkNo
screenNoRaw screen field overrides for the create payload
groupIdNoTarget window group; 0 keeps them ungrouped
proxyIdNoProxy to bind; 0 means no proxy
pluginIdsNo
accountIdsNoPlatform account IDs to bind, so nex_browser_fill_account can sign in later
preferenceNoRaw preference field overrides
startupUrlNo
fingerprintNoRaw fingerprint field overrides

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv2026.11.3
    • changedInput schema / properties / accountIds / anyOf
      Previous value: -[
      -  {
      -    "anyOf": [
      -      {
      -        "type": "string"
      -      },
      -      {
      -        "type": "number"
      -      }
      -    ]
      -  },
      -  {
      -    "items": {
      -      "anyOf": [
      -        {
      -          "type": "string"
      -        },
      -        {
      -          "type": "number"
      -        }
      -      ]
      -    },
      -    "type": "array"
      -  }
      -]New value: +[
      +  {
      +    "type": [
      +      "string",
      +      "number"
      +    ]
      +  },
      +  {
      +    "items": {
      +      "type": [
      +        "string",
      +        "number"
      +      ]
      +    },
      +    "type": "array"
      +  }
      +]
    • removedInput schema / properties / groupId / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "number"
      -  }
      -]
    • addedInput schema / properties / groupId / type
      Added value: +[
      +  "string",
      +  "number"
      +]
    • changedInput schema / properties / pluginIds / anyOf
      Previous value: -[
      -  {
      -    "anyOf": [
      -      {
      -        "type": "string"
      -      },
      -      {
      -        "type": "number"
      -      }
      -    ]
      -  },
      -  {
      -    "items": {
      -      "anyOf": [
      -        {
      -          "type": "string"
      -        },
      -        {
      -          "type": "number"
      -        }
      -      ]
      -    },
      -    "type": "array"
      -  }
      -]New value: +[
      +  {
      +    "type": [
      +      "string",
      +      "number"
      +    ]
      +  },
      +  {
      +    "items": {
      +      "type": [
      +        "string",
      +        "number"
      +      ]
      +    },
      +    "type": "array"
      +  }
      +]
    • removedInput schema / properties / proxyId / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "number"
      -  }
      -]
    • addedInput schema / properties / proxyId / type
      Added value: +[
      +  "string",
      +  "number"
      +]
  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 carries the full behavioral burden, and it does disclose genuine behavior: unset fields inherit the desktop create-window defaults (fingerprint, preferences, layout, startup page) and each window receives its own generated fingerprint. However, it says nothing about whether the created windows are connected/launched, what identifiers come back, permission or quota constraints, or what happens at the schema's 50-window cap.

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?

Two sentences, front-loaded with the action and followed by the override/default rule that an agent actually needs. No wasted clauses, though the sentence structure is slightly dense with the parenthetical default list.

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

Completeness3/5

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

For an 11-parameter, nested-object creation tool with no annotations and no output schema, the description covers input semantics well but leaves the return value and follow-up lifecycle unexplained (e.g., whether the result must be fed into nex_browser_connect or nex_browser_fill_account). The agent has enough to call it, but not enough to chain it confidently.

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?

The 'every unset field falls back to the defaults' rule establishes a semantic model for all eleven optional parameters that the schema does not express, and the fingerprint note clarifies a nested object whose contents are otherwise opaque. Coverage is 73% and the schema already documents count, groupId, proxyId, and accountIds, so the description does not need to repeat them.

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 states a specific verb and resource ('Create NexBrowser environments') and scopes it to 'the desktop app's active workspace', then clarifies with 'each created window'. That cleanly separates it from creation-adjacent siblings like nex_browser_group_create and from launch/open siblings like nex_browser_open or nex_browser_connect.

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

Usage Guidelines3/5

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

'Pass only the fields that must differ' gives real guidance on how to fill the call (minimal overrides), which is more than nothing. But there is no explicit when-to-use vs. when-not, no mention of alternatives such as opening or connecting an existing window, and no preconditions (workspace/desktop app must be running) are stated.

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