Skip to main content
Glama
Sign In
@ainative/browser-mcp

@ainative/browser-mcp

Official
by AINative-Studio
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

@ainative/browser-mcp

AINative Browser Agent MCP Server. Gives AI agents browser automation capabilities — act on pages, extract structured data, validate content, run multi-step tasks, and enrich agent memory from the web.

Auto-detects ZeroLocal (localhost:8000) or AINative Cloud.

Install

npx @ainative/browser-mcp

Or install globally:

npm install -g @ainative/browser-mcp

Related MCP server: Browser Automation MCP

Configure in Claude Code

{
  "mcpServers": {
    "browser": {
      "command": "npx",
      "args": ["@ainative/browser-mcp"],
      "env": {
        "AINATIVE_API_KEY": "ak_your_key_here"
      }
    }
  }
}

Tools

Tool

Description

Credits

browser_act

Perform an action on a web page (click, type, navigate)

50

browser_extract

Extract structured data from a page

75

browser_validate

Validate content or state on a page

25

browser_task

Run a multi-step automation task

200

browser_extract_to_table

Extract data and store in ZeroDB table

100

browser_enrich_memory

Extract content and store in agent memory

100

Authentication

Set one of the following:

# API key (recommended)
AINATIVE_API_KEY=ak_your_key_here

# OR username/password
AINATIVE_USERNAME=you@example.com
AINATIVE_PASSWORD=your_password

Get your API key from ainative.studio/dashboard.

ZeroLocal (Local-First)

The server auto-detects ZeroLocal running on localhost:8000. If ZeroLocal is running, it is used automatically — no configuration needed. Otherwise it falls back to AINative Cloud.

To run ZeroLocal:

pip install zerodb-local
zerodb serve

Examples

Extract product data:

{
  "tool": "browser_extract",
  "arguments": {
    "url": "https://example.com/products",
    "extract_goal": "Extract all product names and prices"
  }
}

Perform an action:

{
  "tool": "browser_act",
  "arguments": {
    "url": "https://example.com",
    "instruction": "Click the sign in button",
    "max_steps": 5
  }
}

Store page content in agent memory:

{
  "tool": "browser_enrich_memory",
  "arguments": {
    "url": "https://example.com/blog/post",
    "extract_goal": "Extract key facts about the product",
    "memory_type": "semantic",
    "project_id": "your-project-id"
  }
}

Links

Available Tools

8 tools
browser_actA

Perform an action on a web page using AI-powered browser automation. Use when you need to click, type, navigate, or otherwise interact with a page. (50 credits)

Inputs: url (required), instruction (required), max_steps.

browser_batch_extractA

Extract structured data from up to 10 URLs in a single call and store rows in a ZeroDB table. Use when you need to scrape multiple pages at once. (75 credits per URL)

Inputs: urls (required), project_id (required), table_name (required), extract_goal (required).

browser_enrich_memoryA

Extract content from a web page and store it in agent memory (ZeroDB). Use when you want an agent to "remember" information from a URL for future recall. (100 credits)

Inputs: url (required), project_id (required), memory_type, extract_goal.

browser_enrich_memory_asyncA

Queue an async browser memory enrichment task. Returns a task_id immediately — the browser visits the URL and stores content in ZeroMemory in the background. (100 credits)

Inputs: url (required), project_id (required), memory_type, extract_goal.

browser_extractA
Read-onlyIdempotent

Extract structured data from a web page. Use when you need to scrape, parse, or retrieve specific information from a URL. Returns data in structured JSON format. (75 credits)

Inputs: url (required), extract_goal (required).

browser_extract_to_tableA

Extract structured data from a web page and store it directly in a ZeroDB NoSQL table. Use when you need to scrape data and persist it for later querying or analysis. (100 credits)

Inputs: url (required), project_id (required), table_name (required), extract_goal (required).

browser_taskA

Run a multi-step browser automation task. Use when you need to perform a complex, multi-step workflow on a web page (e.g. login and fill out a form). More capable than browser_act for complex flows. (200 credits)

Inputs: url (required), task_description (required), max_steps.

browser_validateA
Read-onlyIdempotent

Validate content or state on a web page. Use when you need to assert that specific content exists, a form was submitted, or a page reached an expected state. (25 credits)

Inputs: url (required), assertion (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.9/5.0

    Scored across 8 tools

    Disambiguation3/5

    Several tools involve extracting data from a page (browser_extract, browser_extract_to_table, browser_batch_extract, browser_enrich_memory, browser_enrich_memory_async), and their differences (output format vs. storage destination) may not be immediately clear. Browser_act and browser_task also overlap in describing page interactions. Descriptions help, but boundaries are not perfectly distinct.

    Naming Consistency4/5

    All tools share the 'browser_' prefix and are verb-oriented, giving a consistent feel. However, the structure varies: simple verbs (act, extract, validate), compound verbs (extract_to_table, enrich_memory), and an adjective+verb form (batch_extract). This minor inconsistency is still readable and predictable enough.

    Tool Count5/5

    Eight tools is well within the ideal range and matches the server's purpose of browser automation. Each tool has a specific role in acting, extracting, validating, or persisting data, so the count feels appropriate without being excessive.

    Completeness4/5

    The toolset covers single interactions, complex multi-step workflows, extraction, validation, and persistent storage options, including batch and async variants. Minor gaps like explicit screenshot capture or session/cookie management exist, but the core browser automation lifecycle is well represented.

    Maintenance

    ActivitySlowing
    ResponsivenessLimited data

    Resources

    Related MCP Connectors

    Related MCP Servers