Rube MCP is Composio's multi-tool control plane that lets you discover, connect, and execute tools like Bugherd via standardized MCP calls.

Do I always need to call RUBE_SEARCH_TOOLS before running a Bugherd tool?

Yes, to fetch current tool slugs and input schemas; tool schemas change frequently.

What if the Bugherd connection is not ACTIVE?

Complete the auth flow and confirm ACTIVE status in RUBE_MANAGE_CONNECTIONS before execution.

bugherd-automation

Scanned

npx machina-cli add skill ComposioHQ/awesome-claude-skills/bugherd-automation --openclaw

Files (1)

SKILL.md

2.9 KB

Bugherd Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/bugherd

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active Bugherd connection via RUBE_MANAGE_CONNECTIONS with toolkit bugherd
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.

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

Tool Discovery

Always discover available tools before executing workflows:

RUBE_SEARCH_TOOLS
queries: [{use_case: "Bugherd 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 Bugherd task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["bugherd"]
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 Bugherd-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `bugherd`
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

Source

git clone https://github.com/ComposioHQ/awesome-claude-skills/blob/master/composio-skills/bugherd-automation/SKILL.mdView on GitHub

Overview

Automate Bugherd operations through Composio's Bugherd toolkit via Rube MCP. It relies on RUBE_SEARCH_TOOLS to fetch current tool schemas and requires an active Bugherd connection. Always discover tools first to use up-to-date slugs and arguments.

How This Skill Works

Start by discovering available Bugherd tools and their input schemas with RUBE_SEARCH_TOOLS. Then establish an ACTIVE Bugherd connection using RUBE_MANAGE_CONNECTIONS for the bugherd toolkit. Finally execute a discovered tool with RUBE_MULTI_EXECUTE_TOOL, supplying the schema-compliant arguments, memory, and a session_id.

When to Use It

You need to automate recurring Bugherd tasks (e.g., create, assign, or update tasks) using current tool schemas.
You want to establish or verify a Bugherd connection via Rube MCP before running workflows.
Your workflow requires exact input fields obtained from tool discovery rather than hardcoded values.
You need to reuse a session_id across multiple steps in a single Bugherd workflow.
You are processing large sets of tools or results and must handle pagination tokens.

Quick Start

Step 1: RUBE_SEARCH_TOOLS with a Bugherd use case to fetch current tool slugs and schemas.
Step 2: RUBE_MANAGE_CONNECTIONS with toolkits: ["bugherd"] and a valid session_id, ensuring status ACTIVE.
Step 3: RUBE_MULTI_EXECUTE_TOOL with tool_slug from discovery, the required arguments, memory: {} and session_id from step 2.

Best Practices

Always call RUBE_SEARCH_TOOLS first to fetch current schemas.
Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing tools.
Use exact field names and types from the search results; avoid hardcoding slugs.
Include memory in RUBE_MULTI_EXECUTE_TOOL payload, even if empty ({}).
Reuse session IDs within a workflow and regenerate only for new workflows; watch for pagination.

Example Use Cases

Create a Bugherd task from a summary and assign it to a user.
Automatically update a Bugherd task status when an external event occurs.
Bulk-close completed Bugherd tasks when a milestone is reached.
Synchronize Bugherd tasks with an external issue tracker to mirror state.
Automate repetitive Bugherd edits across multiple projects.

Frequently Asked Questions

Add this skill to your agents