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

SKILL

alchemy-automation

Name: alchemy-automation
Author: Composio

Automate Alchemy tasks via Rube MCP with schema discovery 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 instruction set from a highly trusted GitHub repository, so overall risk is low. However, its actual use depends on remote Rube MCP and Alchemy connections, meaning workflow requests and account authorizations are handled by third-party services and should be scoped carefully.

CredentialsCaution

The material says no local API key or environment variable is required, but it does require an active Alchemy connection via `RUBE_MANAGE_CONNECTIONS`, which typically implies OAuth or managed credentials. The main risk is that once authorized, the third-party connection may act on the user's Alchemy account.

Network egressCaution

The README explicitly requires adding the remote MCP endpoint `https://rube.app/mcp` and using Composio/Rube to search tools, manage connections, and execute workflows. Therefore, task descriptions, arguments, session data, and related Alchemy operation data are sent to declared third-party services rather than handled purely locally.

Code executionLow risk

Based on the material, this skill is a prompt-only guide and does not include local scripts, install commands, or host-side execution logic. It only describes invoking external capabilities through remote MCP tools, with no evidence of spawning local processes or running arbitrary code on the host.

Data accessCaution

There is no indication that it requests local filesystem or system-resource access. However, once the Alchemy connection is ACTIVE, the remote tools can query or operate on the user's Alchemy-side data and resources according to the tool schema, with scope determined by the granted account permissions and specific tools used.

Supply chainLow risk

The source is an open GitHub repository with high community trust (about 64.7k stars), and the material itself is auditable and primarily documentation/prompt content, which are strong risk-reducing factors. The main limitations are an unspecified license and unknown maintenance status, so recent commits and releases should still be checked.

Recommendations

Only connect to `rube.app/mcp` when needed, and review its privacy, logging, and data-handling policies.
Grant Alchemy the minimum necessary permissions, preferably using a separate test account or restricted project.
Before running `RUBE_MULTI_EXECUTE_TOOL`, manually verify the discovered tool schema, arguments, and expected impact.
Regularly review and revoke unused Rube/Alchemy connections and authorizations.

Audited by: gpt-5.4 · 2026-06-16

// install

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

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

// download

Download SKILL.mdInstall manifest ↗

// docs

Alchemy Automation via Rube MCP

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

Toolkit docs: composio.dev/toolkits/alchemy

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["alchemy"]
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 Alchemy-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `alchemy`
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_