How do I ensure tool schemas are current?

Always call RUBE_SEARCH_TOOLS first to fetch current tool slugs and input schemas.

What if the Exa connection is not ACTIVE?

Follow the auth link returned by RUBE_MANAGE_CONNECTIONS to complete setup, then recheck for ACTIVE status before running workflows.

Do I need to include memory in every execute call?

Yes. Include the memory parameter in RUBE_MULTI_EXECUTE_TOOL calls, even if it is empty.

exa-automation

Scanned

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

Files (1)

SKILL.md

2.8 KB

Exa Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/exa

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["exa"]
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 Exa-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `exa`
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/exa-automation/SKILL.mdView on GitHub

Overview

Automate Exa operations via Composio's Exa toolkit using Rube MCP. The workflow emphasizes discovering current tool schemas before execution to avoid hardcoding slugs or arguments.

How This Skill Works

Connect to Rube MCP and ensure Exa toolkit access. Always run RUBE_SEARCH_TOOLS to fetch up-to-date tool schemas, then verify the connection is ACTIVE with RUBE_MANAGE_CONNECTIONS. Finally, use RUBE_MULTI_EXECUTE_TOOL with the discovered tool slug, proper arguments, memory, and session_id to execute the workflow.

When to Use It

You need to automate Exa workflows across multiple tools and updated schemas.
You must verify current tool schemas before execution to avoid mismatches.
You require an ACTIVE Exa connection before running any workflows.
You want to reuse a session within a workflow for efficiency.
You need to handle tool schema pagination to fetch all available tools.

Quick Start

Step 1: Configure Rube MCP endpoint (https://rube.app/mcp) in your client and verify RUBE_SEARCH_TOOLS.
Step 2: Connect to Exa via RUBE_MANAGE_CONNECTIONS and ensure the toolkit is ACTIVE.
Step 3: Discover tools with RUBE_SEARCH_TOOLS, then execute using RUBE_MULTI_EXECUTE_TOOL with memory and SESSION_ID.

Best Practices

Always call RUBE_SEARCH_TOOLS first to obtain current tool slugs and schemas.
Check that RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing tools.
Use exact field names and types from the discovered schemas; avoid hardcoding.
Include memory in every RUBE_MULTI_EXECUTE_TOOL call, even if empty.
Reuse session IDs within a workflow and generate new ones for new workflows.

Example Use Cases

A team automates nightly Exa maintenance by discovering tools with RUBE_SEARCH_TOOLS and executing them via RUBE_MULTI_EXECUTE_TOOL in a single session.
Ops engineers create a reusable Exa workflow that checks service status after establishing an ACTIVE connection to Exa.
A script batches several Exa tasks by first pulling current tool schemas, then executing multiple tools with proper memory handling.
When Exa tool slugs update, the workflow fetches latest slugs with RUBE_SEARCH_TOOLS before running.
For large tool sets, pagination is used to fetch all tool schemas prior to tool selection and execution.

Frequently Asked Questions

Add this skill to your agents