finmei-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/finmei-automation --openclawFinmei Automation via Rube MCP
Automate Finmei operations through Composio's Finmei toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/finmei
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Finmei connection via
RUBE_MANAGE_CONNECTIONSwith toolkitfinmei - Always call
RUBE_SEARCH_TOOLSfirst 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_TOOLSresponds - Call
RUBE_MANAGE_CONNECTIONSwith toolkitfinmei - 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: "Finmei 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 Finmei task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["finmei"]
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_CONNECTIONSshows ACTIVE status before executing tools - Schema compliance: Use exact field names and types from the search results
- Memory parameter: Always include
memoryinRUBE_MULTI_EXECUTE_TOOLcalls, 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 Finmei-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit finmei |
| 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
Source
git clone https://github.com/ComposioHQ/awesome-claude-skills/blob/master/composio-skills/finmei-automation/SKILL.mdView on GitHub Overview
Automate Finmei operations through Composio's Finmei toolkit via Rube MCP. Always search tool schemas first to stay aligned with current capabilities.
How This Skill Works
Set up Rube MCP by adding the MCP server and confirming tool availability with RUBE_SEARCH_TOOLS. Manage the Finmei connection with RUBE_MANAGE_CONNECTIONS and ensure status is ACTIVE. Then discover tools, verify the connection, and execute tools with RUBE_MULTI_EXECUTE_TOOL, including memory and the session_id.
When to Use It
- When starting a Finmei automation, first run RUBE_SEARCH_TOOLS to obtain current tool schemas.
- When you need to ensure integrations are ready, verify RUBE_MANAGE_CONNECTIONS shows ACTIVE before running workflows.
- When executing a tool, reference the discovered tool_slug and schema-compliant arguments via RUBE_MULTI_EXECUTE_TOOL.
- When building multi-step Finmei workflows, reuse a session_id to maintain context across steps.
- When tool schemas change, re-run RUBE_SEARCH_TOOLS instead of hard-coding slugs or args.
Quick Start
- Step 1: Add the MCP server (https://rube.app/mcp) and verify RUBE_SEARCH_TOOLS responds for Finmei.
- Step 2: Call RUBE_MANAGE_CONNECTIONS with toolkits: ["finmei"] and ensure status is ACTIVE.
- Step 3: Discover a tool slug from RUBE_SEARCH_TOOLS and run it with RUBE_MULTI_EXECUTE_TOOL, including a valid memory object and the session_id.
Best Practices
- Always call RUBE_SEARCH_TOOLS before executing to fetch current tool slugs and required args.
- Check that the Finmei toolkit connection is ACTIVE via RUBE_MANAGE_CONNECTIONS before any run.
- Use exact field names and types from the tool schemas; avoid guessing.
- Include a memory object in every RUBE_MULTI_EXECUTE_TOOL call, even if empty.
- Reuse session IDs within a workflow and fetch pagination tokens if responses are paginated.
Example Use Cases
- Automate a Finmei reconciliation by discovering tools with RUBE_SEARCH_TOOLS and executing a matching slug via RUBE_MULTI_EXECUTE_TOOL.
- Establish an ACTIVE Finmei connection using RUBE_MANAGE_CONNECTIONS, then run a sequence of Finmei tools in a single session.
- Fetch and compare multiple tool schemas with RUBE_GET_TOOL_SCHEMAS to adapt workflows to schema changes.
- Perform bulk Finmei tasks by leveraging RUBE_REMOTE_WORKBENCH and run_composio_tool for batch execution.
- Single-step execution: discover, connect, then execute one tool using the exact input schema retrieved earlier.