home / skills / composiohq / awesome-claude-skills / anchor-browser-automation

anchor-browser-automation skill

/anchor-browser-automation

This skill automates Anchor Browser tasks through Composio's Rube MCP, always discovering current tool schemas before execution.

npx playbooks add skill composiohq/awesome-claude-skills --skill anchor-browser-automation

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
3.0 KB
---
name: anchor-browser-automation
description: "Automate Anchor Browser tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Anchor Browser Automation via Rube MCP

Automate Anchor Browser operations through Composio's Anchor Browser toolkit via Rube MCP.

**Toolkit docs**: [composio.dev/toolkits/anchor_browser](https://composio.dev/toolkits/anchor_browser)

## Prerequisites

- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Anchor Browser connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `anchor_browser`
- Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas

## Setup

**Get Rube MCP**: Add `https://rube.app/mcp` as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.

1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds
2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `anchor_browser`
3. If connection is not ACTIVE, follow the returned auth link to complete setup
4. Confirm connection status shows ACTIVE before running any workflows

## Tool Discovery

Always discover available tools before executing workflows:

```
RUBE_SEARCH_TOOLS
queries: [{use_case: "Anchor Browser operations", known_fields: ""}]
session: {generate_id: true}
```

This returns available tool slugs, input schemas, recommended execution plans, and known pitfalls.

## Core Workflow Pattern

### Step 1: Discover Available Tools

```
RUBE_SEARCH_TOOLS
queries: [{use_case: "your specific Anchor Browser task"}]
session: {id: "existing_session_id"}
```

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["anchor_browser"]
session_id: "your_session_id"
```

### Step 3: Execute Tools

```
RUBE_MULTI_EXECUTE_TOOL
tools: [{
  tool_slug: "TOOL_SLUG_FROM_SEARCH",
  arguments: {/* schema-compliant args from search results */}
}]
memory: {}
session_id: "your_session_id"
```

## Known Pitfalls

- **Always search first**: Tool schemas change. Never hardcode tool slugs or arguments without calling `RUBE_SEARCH_TOOLS`
- **Check connection**: Verify `RUBE_MANAGE_CONNECTIONS` shows ACTIVE status before executing tools
- **Schema compliance**: Use exact field names and types from the search results
- **Memory parameter**: Always include `memory` in `RUBE_MULTI_EXECUTE_TOOL` calls, even if empty (`{}`)
- **Session reuse**: Reuse session IDs within a workflow. Generate new ones for new workflows
- **Pagination**: Check responses for pagination tokens and continue fetching until complete

## Quick Reference

| Operation | Approach |
|-----------|----------|
| Find tools | `RUBE_SEARCH_TOOLS` with Anchor Browser-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `anchor_browser` |
| Execute | `RUBE_MULTI_EXECUTE_TOOL` with discovered tool slugs |
| Bulk ops | `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` |
| Full schema | `RUBE_GET_TOOL_SCHEMAS` for tools with `schemaRef` |

---
*Powered by [Composio](https://composio.dev)*

Overview

This skill automates Anchor Browser tasks through Composio’s Anchor Browser toolkit via the Rube MCP. It provides a clear workflow for discovering tools, validating connections, and executing operations reliably. The skill emphasizes dynamic discovery of tool schemas and safe execution patterns to avoid breaking changes. It is suited for programmatic browser automation inside Claude-powered agent workflows.

How this skill works

The skill first calls RUBE_SEARCH_TOOLS to retrieve the current tool slugs, input schemas, and recommended execution plans. It then verifies an active Anchor Browser connection with RUBE_MANAGE_CONNECTIONS and follows returned auth links if needed. Executions are performed with RUBE_MULTI_EXECUTE_TOOL or RUBE_REMOTE_WORKBENCH using the schema-compliant arguments returned by the search. The skill enforces session reuse, memory inclusion, and pagination handling to ensure reliable runs.

When to use it

  • Automating browsing tasks that require Anchor Browser tooling inside an agent workflow.
  • When tool schemas may change and you need up-to-date inputs before execution.
  • Coordinating multi-step browser operations that require authenticated connections.
  • Running bulk or orchestrated browser operations via Composio tooling.
  • Integrating Anchor Browser capabilities into Claude-based automation pipelines.

Best practices

  • Always call RUBE_SEARCH_TOOLS first to fetch current tool slugs and input schemas.
  • Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE for the anchor_browser toolkit before executing tools.
  • Include a memory object (even {}) in RUBE_MULTI_EXECUTE_TOOL calls.
  • Reuse session IDs within a workflow; create new sessions for separate workflows.
  • Follow pagination tokens in responses until data is fully retrieved.

Example use cases

  • Perform site crawling and data extraction using Anchor Browser tools discovered at runtime.
  • Automate authenticated workflows (login, navigate, capture) after confirming the Anchor Browser connection.
  • Execute batched operations via RUBE_REMOTE_WORKBENCH for large-scale browser tasks.
  • Retrieve full tool schemas with RUBE_GET_TOOL_SCHEMAS before building complex argument structures.
  • Create resilient agent steps that adapt to evolving tool inputs and pagination.

FAQ

Do I need API keys to connect to Rube MCP?

No. Add https://rube.app/mcp as an MCP server in your client configuration; no API keys are required.

What happens if I skip RUBE_SEARCH_TOOLS?

Tool slugs or input fields may have changed and your execution can fail. Always discover tools first to avoid schema mismatch.