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

SKILL

serply-automation

Name: serply-automation
Author: Composio

Automate Serply tasks via Rube MCP after checking 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

The skill material itself is an open-source, prompt-only usage guide with no clear red flags for local execution, direct secret injection, or local file access, so overall risk is relatively low. The main caution is that actual data flow and permissions depend on the external Rube MCP and Serply connection.

CredentialsCaution

The material says no local API key or environment variables are needed, but it requires an active `serply` connection via `RUBE_MANAGE_CONNECTIONS` and an authentication link flow. This suggests credentials are managed by Rube/Serply rather than exposed in the skill itself; there is no direct red flag of secret harvesting, but normal third-party authorization and token misuse considerations remain.

Network egressCaution

The README explicitly requires adding the remote MCP endpoint `https://rube.app/mcp` and using Composio/Serply tooling for search, connection management, and tool execution. User requests, session IDs, tool arguments, and related business data are therefore likely sent through this external service chain; this is a normal MCP characteristic, though the material does not define the data handling boundaries in detail.

Code executionLow risk

Per the provided checks, this is a prompt-only skill; the material merely instructs how to call existing MCP tools and does not claim local process spawning, script execution, or system-level execution permissions. The mention of `RUBE_REMOTE_WORKBENCH` indicates remote tool capability, not evidence of local code execution by the skill itself.

Data accessCaution

There is no indication that the skill directly reads or writes local files, clipboard contents, or system resources; however, once connected to `serply`, it can access and automate Serply data and operations through Rube/Composio. The effective data scope therefore depends on the permissions granted by the connected account, which is worth noting but not inherently overprivileged from the material alone.

Supply chainLow risk

The source is an open-source GitHub repository with strong community adoption (64.7k stars), both of which are meaningful risk-reducing signals. The skill content available for review is primarily documentation/prompting; although the license is undeclared, maintenance status is unknown, and actual execution depends on external Rube/Composio services, the provided material shows no clear supply-chain red flags.

Recommendations

Connect to `https://rube.app/mcp` only when needed, and verify the privacy policy and data handling scope of the endpoint, Composio, and Serply.
Apply least-privilege authorization to the Serply connection, and regularly review/revoke third-party connections or tokens that are no longer needed.
Before production use, validate the real tool scope and schemas returned by `RUBE_SEARCH_TOOLS` with low-sensitivity test data.
For higher assurance, audit the Rube MCP, the Composio toolkit, and actual invocation logs rather than relying only on this skill README.

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

// download

Download SKILL.mdInstall manifest ↗

// docs

Serply Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/serply

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["serply"]
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 Serply-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `serply`
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 Amazon tasks through Rube MCP after checking current tool schemas.

ComposioGet→

$ loading_