How to Use the Browse AI MCP in Claude Code

Q: How do I add the Browse AI server to Claude Code?

Run the command claude mcp add --transport http browse-ai -- in your terminal. This adds the configuration to your /.claude.json file and makes all ten extraction tools immediately available.

Q: Does Claude Code support background Browse AI tasks?

Yes, the agent can call runrobot to start a task and then free up your terminal. You can check back later and ask the agent to run gettask to retrieve the completed web data.

Q: How do I check if the scraping platform is experiencing downtime?

You can ask the agent to run getsystemstatus directly from your terminal. It will query the API and return the current status of the queue and system engines.

Run Browse AI robots, track bulk jobs, and pipe extracted web data directly into your terminal pipelines with Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browse AI MCP to Claude Code

Create your Vinkius account to connect Browse AI to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Browse AI with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Terminal-Driven Web Extraction Pipelines

This Browse AI MCP Server gives your CLI agent direct access to your web scraping robots. You can trigger data extraction tasks with `run_robot` and pipe the resulting JSON payloads directly into local shell scripts or files. Because the CLI operates in a headless terminal environment, you can run complex extraction workflows without opening a browser. The agent tracks the status of your jobs in real-time by polling `get_task`.

Command-Line Robot Auditing

Manage your entire web scraping fleet directly from your terminal prompt using `list_robots`. Your CLI agent uses this tool to view your active extraction bots and `get_robot` to inspect the parameters of a specific crawler. This makes it easy to audit your setup before running high-volume jobs. The agent can quickly check which robots are approved and verify their configuration schema without you leaving the command line.

Automated Monitor Management for Claude Code

Integrate web change monitoring into your terminal workflows using `list_monitors` and `create_monitor`. The CLI agent can verify that your site-tracking jobs are active and set up new schedules as part of your deployment scripts. If a monitor goes offline, the agent can troubleshoot the configuration by running `get_system_status` over the MCP connection. The agent can then inspect the configuration of the specific robot to troubleshoot the parameters.

Setup guide

Set up Browse AI MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see browse-ai-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Browse AI transactions." It will automatically discover and invoke the available Browse AI tools.

Terminal

claude mcp add --transport http browse-ai-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Browse AI MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "browse-ai-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Browse AI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Browse AI now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Browse AI MCP in Claude Code

Run the command `claude mcp add --transport http browse-ai -- ` in your terminal. This adds the configuration to your `~/.claude.json` file and makes all ten extraction tools immediately available.

Yes, you can instruct the CLI agent to initiate bulk runs and monitor them using `list_bulk_runs`. The agent can poll `get_bulk_run` and output the results directly to your standard output or a local file.

Yes, the agent can call `run_robot` to start a task and then free up your terminal. You can check back later and ask the agent to run `get_task` to retrieve the completed web data.

You can ask the agent to run `get_system_status` directly from your terminal. It will query the API and return the current status of the queue and system engines.

The MCP Server uses a zero-trust architecture where all data transfers are encrypted in transit. The scraped payloads, robot configurations, and scheduling parameters are processed on ephemeral Vinkius infrastructure that never retains your data post-execution.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript