instacart-automation
Scannednpx machina-cli add skill ComposioHQ/awesome-claude-skills/instacart-automation --openclawInstacart Automation via Rube MCP
Automate Instacart operations through Composio's Instacart toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/instacart
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Instacart connection via
RUBE_MANAGE_CONNECTIONSwith toolkitinstacart - 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 toolkitinstacart - 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: "Instacart 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 Instacart task"}]
session: {id: "existing_session_id"}
Step 2: Check Connection
RUBE_MANAGE_CONNECTIONS
toolkits: ["instacart"]
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 Instacart-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit instacart |
| 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/instacart-automation/SKILL.mdView on GitHub Overview
Automate Instacart operations through Composio's Instacart toolkit via Rube MCP. Always search for current tool schemas before running workflows to avoid hardcoding slugs or arguments. This approach keeps automation resilient to schema changes and streamlines setup.
How This Skill Works
Start by discovering available Instacart tools with RUBE_SEARCH_TOOLS to obtain current tool slugs and input schemas. Next, verify an ACTIVE Instacart connection using RUBE_MANAGE_CONNECTIONS. Finally, execute the chosen tool(s) with RUBE_MULTI_EXECUTE_TOOL, supplying the schema-compliant arguments and a memory object, and reuse a session_id across the workflow. Tool schemas and required fields are derived from the search results, ensuring correct payloads.
When to Use It
- Automating recurring Instacart tasks (e.g., order placement or cart management) by dynamically discovering tools at runtime.
- When tool schemas change frequently; re-fetch schemas before each workflow to avoid hardcoded slugs and arguments.
- After establishing an ACTIVE connection to Instacart, execute workflows to perform tasks.
- Perform batch or bulk Instacart operations using multi-tool execution or bulk benches.
- Handle pagination or large result sets by continuing fetches and reusing session IDs within a workflow.
Quick Start
- Step 1: Add https://rube.app/mcp as an MCP server and verify RUBE_SEARCH_TOOLS is accessible.
- Step 2: Run RUBE_SEARCH_TOOLS with a use_case like 'Instacart operations' to discover available tools and input schemas.
- Step 3: Ensure the connection is ACTIVE via RUBE_MANAGE_CONNECTIONS, then execute a discovered tool with RUBE_MULTI_EXECUTE_TOOL, including memory and a session_id.
Best Practices
- Always call RUBE_SEARCH_TOOLS before starting a workflow to get current tool slugs and input schemas.
- Verify the Instacart connection is ACTIVE via RUBE_MANAGE_CONNECTIONS before executing tools.
- Use exact field names and types from the search results; avoid hardcoding arguments.
- Include memory in every RUBE_MULTI_EXECUTE_TOOL call, even if empty.
- Reuse session IDs within a workflow and manage pagination tokens when present.
Example Use Cases
- Discover the place_order tool from the Instacart toolset and execute it with discovered arguments to automate a weekly grocery order.
- Update an order's status by running update_order_status with the required order_id and status values derived from the tool schema.
- Fetch delivery windows for multiple stores using get_delivery_windows and handle pagination until all windows are retrieved.
- Run multiple Instacart tasks in one session using RUBE_MULTI_EXECUTE_TOOL and memory to automate a pickup, payment, and confirmation flow.
- If tool schemas change, re-discover tools with RUBE_SEARCH_TOOLS and re-run the workflow with updated arguments.
