$ ~/registry/skill/composiohq-composio-skills-tavily-automation

SKILL

tavily-automation

Name: tavily-automation
Author: Composio

Automate Tavily search tasks through Rube MCP within your workflows.

Stars

★ 67,763

Source

GitHub

Updated

2026-07-15

// securityCaution

Prompt only, no code
Open source
Community-trusted· 64.7k

Summary

The material appears to be primarily prompt-like guidance for using Rube MCP/Composio Tavily tooling, with no direct local secret requirement and no explicit local execution or file access described. Overall risk is lowered by strong open-source/community trust signals, though real behavior depends on external Rube MCP and Tavily integrations, which introduces normal third-party service and supply-chain considerations.

CredentialsCaution

The material claims 'No API keys needed,' but it also requires creating and activating a `tavily` connection via `RUBE_MANAGE_CONNECTIONS` and following an auth link, implying credentials may be handled through an external connection flow rather than truly absent. No direct in-skill secret entry is described, so this is a normal third-party auth caution.

Network egressCaution

The README explicitly requires connecting to the remote MCP endpoint `https://rube.app/mcp` and interacting with Composio/Rube and Tavily tooling; task arguments, session IDs, tool discovery queries, and execution data may be sent to those declared external services. No unrelated or hidden exfiltration endpoint is stated, but normal outbound data transfer is involved.

Code executionLow risk

System checks mark this as prompt-only, and the provided content is mainly workflow and parameter guidance without describing local process spawning, script execution, shell commands, or elevated system permissions. `RUBE_REMOTE_WORKBENCH` is only mentioned as a reference operation, with no factual basis here that this skill itself executes local code.

Data accessLow risk

The material does not claim direct access to local files, databases, clipboard, or other host resources; the data surface appears limited to MCP session inputs such as tool queries, connection status, and execution arguments. No overbroad local data access beyond the Tavily automation use case is described.

Supply chainLow risk

The source is an open GitHub repository with very strong community adoption (64.7k stars), which is a significant risk-lowering factor; the material also looks like skill documentation rather than a closed executable artifact. Caveats remain around the unspecified license, unknown maintenance status, and dependency on multiple external services (Rube MCP/Composio/Tavily), but no concrete red flags justify a high-risk rating from the available facts.

Recommendations

Before use, verify the official privacy and data-handling policies for `rube.app/mcp`, Composio, and Tavily, and avoid sending sensitive business content.
When authorizing the `tavily` connection, review the OAuth/connection permission scope and grant only the minimum access required.
Prefer testing this skill in an isolated environment and log what queries/parameters are sent through MCP and what data is returned.
Before production use, additionally review repository maintenance activity, license status, and the actual implementation of the related Rube MCP/Composio tooling.

Audited by: gpt-5.4 · 2026-06-17

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "tavily-automation" skill from askskill:
1. Download https://raw.githubusercontent.com/ComposioHQ/awesome-claude-skills/master/composio-skills/tavily-automation/SKILL.md
2. Save it as ~/.claude/skills/tavily-automation/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// docs

Tavily Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/tavily

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["tavily"]
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 Tavily-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `tavily`
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

Automate Code Interpreter workflows for coding, analysis, and repeatable task execution.

ComposioGet→

$ loading_