docsumo-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/docsumo-automation --openclawDocsumo Automation via Rube MCP
Automate Docsumo operations through Composio's Docsumo toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/docsumo
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Docsumo connection via
RUBE_MANAGE_CONNECTIONSwith toolkitdocsumo - 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 toolkitdocsumo - 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: "Docsumo 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 Docsumo task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["docsumo"]
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 Docsumo-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit docsumo |
| 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/docsumo-automation/SKILL.mdView on GitHub Overview
Automate Docsumo operations through Composio's Docsumo toolkit via Rube MCP. Always search for current tool schemas first using RUBE_SEARCH_TOOLS to stay aligned with updated slugs and input schemas.
How This Skill Works
Connect Rube MCP and Docsumo toolkit, then discover available tools with RUBE_SEARCH_TOOLS. Validate the connection with RUBE_MANAGE_CONNECTIONS, then execute the chosen tool via RUBE_MULTI_EXECUTE_TOOL using the discovered slug and memory payload. Always reuse or generate a session ID and confirm ACTIVE status before running workflows.
When to Use It
- Automating the extraction of data from a batch of invoices, forms, or contracts using Docsumo tools.
- Initial integration of Docsumo tasks into an MVP workflow, where tool slugs and schemas must be discovered first.
- Running bulk document processing while maintaining a session across multiple documents.
- Validating and reconciling extracted fields against downstream databases or CRMs after each run.
- Troubleshooting tool schemas or pagination in Docsumo tool responses and adjusting inputs accordingly.
Quick Start
- Step 1: RUBE_SEARCH_TOOLS queries: [{use_case: "Docsumo operations", known_fields: ""}] and confirm tool slugs and input schemas.
- Step 2: RUBE_MANAGE_CONNECTIONS with toolkits: ["docsumo"] and verify the session becomes ACTIVE.
- Step 3: RUBE_MULTI_EXECUTE_TOOL with the discovered tool_slug, proper arguments from the schema, memory: {}, and the active session_id.
Best Practices
- Always call RUBE_SEARCH_TOOLS first to fetch current tool slugs and input schemas.
- Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing any tools.
- Use exact field names and types from the search results, and avoid hardcoding slugs.
- Include memory in every RUBE_MULTI_EXECUTE_TOOL call, even if empty.
- Reuse session IDs within a workflow and generate new ones for new workflows; monitor pagination and continue fetching tokens as needed.
Example Use Cases
- Process 500 invoices: discover the Docsumo invoice tool, connect, then run the tool to extract line items and totals, storing results in a data store.
- Audit contract summaries: discover the contract extraction tool, validate terms and parties, and push results to a CRM via a downstream step.
- Batch form digitization: fetch available form extraction tools, execute on a batch, and accumulate results with a single session across documents.
- Data validation workflow: extract fields from documents and compare against a reference dataset, flagging mismatches for review.
- Retry failed documents: reuse an existing session to reprocess documents that produced partial results, ensuring memory is populated for stateful runs.