Odel
ainative browser mcp

ainative browser mcp

Local
@ainative-studioJavaScriptMITUpdated 1mo ago

AI-powered browser automation MCP — 6 tools for web interaction, extraction, and validation.

@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

Configure in Claude Code

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

Tools

ToolDescriptionCredits
browser_actPerform an action on a web page (click, type, navigate)50
browser_extractExtract structured data from a page75
browser_validateValidate content or state on a page25
browser_taskRun a multi-step automation task200
browser_extract_to_tableExtract data and store in ZeroDB table100
browser_enrich_memoryExtract content and store in agent memory100

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