home / skills / composiohq / awesome-claude-skills / bolna-automation

bolna-automation skill

safe

/bolna-automation

This skill automates Bolna tasks through Rube MCP by discovering tool schemas first and ensuring active connections before execution.

npx playbooks add skill composiohq/awesome-claude-skills --skill bolna-automation

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

Files (1)

SKILL.md

2.8 KB

---
name: bolna-automation
description: "Automate Bolna tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Bolna Automation via Rube MCP

Automate Bolna operations through Composio's Bolna toolkit via Rube MCP.

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

## Prerequisites

- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Bolna connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `bolna`
- 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 `bolna`
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: "Bolna 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 Bolna task"}]
session: {id: "existing_session_id"}
```

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["bolna"]
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 Bolna-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `bolna` |
| 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 Bolna operations by driving Composio’s Bolna toolkit through a Rube MCP connection. It standardizes discovery, connection management, and tool execution so workflows are repeatable and schema-safe. Always search for current tool schemas before acting to avoid runtime failures.

How this skill works

The skill first calls RUBE_SEARCH_TOOLS to fetch available Bolna tool slugs, input schemas, execution plans, and pagination tokens. It verifies or establishes an active Bolna connection via RUBE_MANAGE_CONNECTIONS. Finally it runs tools using RUBE_MULTI_EXECUTE_TOOL (or RUBE_REMOTE_WORKBENCH for bulk jobs), always passing schema-compliant arguments, a memory object, and a session_id.

When to use it

Automating routine Bolna tasks that require up-to-date tool schemas
Running multi-step Bolna workflows where session reuse matters
Executing bulk operations via Composio tools from a centralized MCP
Integrating Bolna actions into larger agent-driven pipelines
When you need robust connection and schema validation before execution

Best practices

Always run RUBE_SEARCH_TOOLS first; never hardcode tool slugs or argument shapes
Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE for the bolna toolkit before executing tools
Include a memory object (even {} ) in RUBE_MULTI_EXECUTE_TOOL calls
Reuse session_id for related workflow steps; generate a new session for separate workflows
Handle pagination tokens from search responses and fetch until complete

Example use cases

Discover available Bolna actions and programmatically build a workflow using returned schemas
Connect and authenticate the Bolna toolkit, then run a sequence of Bolna API calls via RUBE_MULTI_EXECUTE_TOOL
Perform bulk data operations with RUBE_REMOTE_WORKBENCH and run_composio_tool() for high-throughput jobs
Integrate Bolna task execution into a Claude-driven agent that dynamically queries tool capabilities
Automate a multi-step Bolna maintenance routine while preserving session context and memory

FAQ

What do I do if RUBE_SEARCH_TOOLS returns different schemas than before?

Treat the new schemas as authoritative: update argument construction to match field names and types, and avoid using cached slugs or payload shapes.

Is an API key required to connect to Rube MCP?

No API key is required; add https://rube.app/mcp as an MCP server in your client configuration and use RUBE_MANAGE_CONNECTIONS to activate the bolna toolkit.