Do I need API keys to use Fidel API automation?

No API keys are required. Add the MCP endpoint, ensure RUBE_SEARCH_TOOLS can discover tools, and establish an active Fidel API connection with RUBE_MANAGE_CONNECTIONS.

Should I always include memory in execution calls?

Yes. Include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty, to preserve execution context.

How do I know which tool slugs to run?

Use RUBE_SEARCH_TOOLS to discover available Fidel API tools and their input schemas; never hardcode slugs or arguments.

fidel-api-automation

Scanned

npx machina-cli add skill ComposioHQ/awesome-claude-skills/fidel-api-automation --openclaw

Files (1)

SKILL.md

2.9 KB

Fidel API Automation via Rube MCP

Automate Fidel API operations through Composio's Fidel API toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/fidel_api

Prerequisites

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

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["fidel_api"]
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 Fidel API-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `fidel_api`
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/fidel-api-automation/SKILL.mdView on GitHub

Overview

Automate Fidel API tasks end-to-end using Composio's Fidel API toolkit via Rube MCP. It emphasizes discovering current tool schemas with RUBE_SEARCH_TOOLS before running workflows and validating a live Fidel API connection with RUBE_MANAGE_CONNECTIONS.

How This Skill Works

You first discover available Fidel API tools with RUBE_SEARCH_TOOLS to get current input schemas. Then verify or establish the Fidel API connection using RUBE_MANAGE_CONNECTIONS with the fidel_api toolkit. Finally, execute the chosen tool with RUBE_MULTI_EXECUTE_TOOL, supplying the tool_slug, schema-compatible arguments, a memory object, and the session_id.

When to Use It

When building automated Fidel API workflows that must adapt to current tool schemas
When onboarding Fidel API tasks and validating a live connection before execution
When discovering tool slugs and input schemas for a new Fidel API workflow
When executing a batch of Fidel API operations across multiple tools in a single session
When debugging tool execution and avoiding hardcoded slugs by always querying current schemas

Quick Start

Step 1: RUBE_SEARCH_TOOLS for Fidel API operations to reveal current tool schemas
Step 2: RUBE_MANAGE_CONNECTIONS with fidel_api and confirm ACTIVE
Step 3: RUBE_MULTI_EXECUTE_TOOL using the discovered tool_slug and memory, with the session_id

Best Practices

Always call RUBE_SEARCH_TOOLS first to get current tool schemas and avoid hardcoding slugs
Check that RUBE_MANAGE_CONNECTIONS shows ACTIVE before executing tools
Use exact field names and types from the tool schemas returned by search results
Include the memory parameter in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})
Reuse session IDs within a workflow and create new ones only for new workflows

Example Use Cases

Automate creating a Fidel API customer by discovering a create_customer tool slug, then executing it with the required arguments
Retrieve an account balance using a discovered tool and parse the response
List Fidel accounts in a paginated response using a list_accounts tool and handle pagination tokens
Update a Fidel API setting by discovering an update_setting tool and running it with the correct args
Run a batch of Fidel API operations by discovering multiple tools and executing them in a single RUBE_MULTI_EXECUTE_TOOL session

Frequently Asked Questions

Add this skill to your agents