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

SKILL

perplexityai-automation

Name: perplexityai-automation
Author: Composio

Automate PerplexityAI queries and information workflows through Rube MCP.

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 an open-source prompt/workflow wrapper and does not itself include local execution logic or static key requirements. However, it is explicitly designed to rely on remote Rube MCP/Composio tool calls and downstream third-party authorization, so the overall posture is low-to-moderate concern, mainly due to the external service chain rather than the skill text itself.

CredentialsCaution

The material says 'No API keys needed,' but it also requires creating an ACTIVE `perplexityai` connection via `RUBE_MANAGE_CONNECTIONS` and completing an auth link. This implies credentials are likely handled through the external MCP/Composio connection flow. The skill itself does not expose static secret fields, but there is the usual credential risk associated with delegated third-party account authorization.

Network egressCaution

The README explicitly instructs users to add the remote MCP endpoint `https://rube.app/mcp` and execute operations through the Composio/Perplexityai toolchain. Although the system metadata says no remote host, the documentation shows requests and task parameters will be sent to Rube/Composio and the downstream Perplexityai service. This is normal outbound traffic for this kind of automation skill, with no extra unknown exfiltration endpoint evident in the provided material.

Code executionLow risk

The system flags this as prompt-only, and the content is a workflow guide plus tool-call examples. It does not show local scripts, shell commands, installers, or bundled executable code. Any execution capability depends on external MCP tools rather than the skill directly spawning local processes.

Data accessCaution

The skill text does not claim direct access to local files or system data, but it will pass user task descriptions, parameters, session IDs, and possibly result/pagination data to remote MCP services and authorized Perplexityai tools. There is no visible request for local file or system permissions beyond the stated purpose, so this is a standard data-delegation concern rather than clear over-privilege.

Supply chainLow risk

The source is a GitHub open-source repository, and the system reports both open-source status and strong community adoption (64.7k stars), which are meaningful risk-reducing signals. The material appears to be a skill entry within `awesome-claude-skills`; although the license is unspecified and maintenance status is unknown, and actual runtime depends on external Rube/Composio services, the skill text itself is relatively low risk from a source and auditability perspective.

Recommendations

Before enabling it, verify the privacy policy, data retention, and authorization scope for `rube.app/mcp`, Composio, and Perplexityai.
Authorize the Perplexityai connection only when needed, preferably with least-privilege or easily revocable access.
Do not include unnecessary sensitive data in task arguments, especially internal documents, customer data, or long-lived credentials.
If possible, inspect the actual Rube tool list and schemas exposed to this skill before deciding to use it.

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

// download

Download SKILL.mdInstall manifest ↗

// docs

Perplexityai Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/perplexityai

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["perplexityai"]
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 Perplexityai-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `perplexityai`
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 Recallai workflows through Rube MCP with tool-schema lookup first.

ComposioGet→

$ loading_