$ ~/registry/skill/composiohq-composio-skills-remote-retrieval-automation

SKILL

remote-retrieval-automation

Name: remote-retrieval-automation
Author: Composio

Automate remote retrieval workflows via Rube MCP using current tool schemas first.

Stars

★ 67,763

Source

GitHub

Updated

2026-07-15

// securityCaution

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

Summary

This skill appears to be primarily prompt/instruction content, open-source, and backed by strong community trust, so overall risk is relatively low. However, it explicitly routes usage through third-party Rube MCP and Remote Retrieval connections, which introduces remote service access, connection authorization, and potential data egress that should be verified before use.

CredentialsCaution

The material says no API keys are needed, but the README explicitly requires establishing a `remote_retrieval` connection via `RUBE_MANAGE_CONNECTIONS` and following a returned auth link if inactive. This means the skill itself may not collect keys directly, but the workflow can still involve third-party OAuth or connection tokens, so authorization scope and token custody should be reviewed.

Network egressCaution

The README explicitly instructs adding `https://rube.app/mcp` as an MCP server and using Composio/Rube remote tooling for retrieval and workflow execution. User inputs, query parameters, session IDs, and tool-call arguments are therefore likely sent to that third-party endpoint. The material does not provide more detailed data-flow documentation, so this is a typical remote egress case that warrants caution.

Code executionLow risk

Based on the provided material, this skill itself is prompt-only guidance and does not include executable code, install scripts, or local shell execution steps. Its core function is to instruct use of existing MCP tools rather than directly spawning local processes or executing arbitrary code on the host.

Data accessCaution

The skill is centered on Remote Retrieval automation and requires activating the relevant connection first. This means the effective data access scope depends on the connected remote retrieval tool and the permissions granted to that account. The material does not specify exactly which resources can be read, or whether write/delete operations are possible, so the scope is somewhat opaque but not explicitly over-privileged from the evidence shown.

Supply chainLow risk

The source is an open GitHub repository, and the system marks it as `open-source` with high community adoption (64.7k stars), which are strong positive trust signals. Although the license is unspecified and maintenance status is unknown, the provided material shows no clear red flags such as closed-source exfiltration, malicious installation behavior, or obvious prompt-injection style abuse, so supply-chain risk is overall low.

Recommendations

Before connecting, verify the privacy policy, data retention, and logging practices of `rube.app/mcp` and Composio Remote Retrieval.
When completing `RUBE_MANAGE_CONNECTIONS` authorization, use the minimum required scope and periodically review or revoke unused connections.
Avoid sending highly sensitive data in tool queries or sessions; validate actual egress behavior and responses with test data first.
Review the relevant open-source repository, tool docs, and connection permission details to confirm the skill is only orchestration guidance and does not hide extra execution logic.

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

// download

Download SKILL.mdInstall manifest ↗

// docs

Remote Retrieval Automation via Rube MCP

Automate Remote Retrieval operations through Composio's Remote Retrieval toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/remote_retrieval

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["remote_retrieval"]
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 Remote Retrieval-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `remote_retrieval`
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 Composio tasks via Rube MCP with tool schema lookup first.

ComposioGet→

$ loading_