Skip to main content
NEW · APP STORE Now on iOS · macOS · iPad Android & Windows soon GET IT
Prompts Blocknative Automation via Rube MCP

agent tool_use skill risk: medium

Blocknative Automation via Rube MCP

Provides instructions for automating Blocknative operations through Composio's toolkit via Rube MCP, including prerequisites, setup steps, tool discovery with RUBE_SEARCH_TOOLS, co…

  • Policy sensitive
  • Human review
  • External action: high

SKILL 1 file

SKILL.md
---
name: blocknative-automation
description: "Automate Blocknative tasks via Rube MCP (Composio). Always search tools first for current schemas."
---
# Blocknative Automation via Rube MCP

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

**Toolkit docs**: [composio.dev/toolkits/blocknative](https://composio.dev/toolkits/blocknative)

## Prerequisites

- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Blocknative connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `blocknative`
- 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.

1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds
2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `blocknative`
3. If connection is not ACTIVE, follow the returned auth link to complete setup
4. Confirm connection status shows ACTIVE before running any workflows

## Tool Discovery

Always discover available tools before executing workflows:

```
RUBE_SEARCH_TOOLS
queries: [{use_case: "Blocknative 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 Blocknative task"}]
session: {id: "existing_session_id"}
```

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["blocknative"]
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 Blocknative-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `blocknative` |
| 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](https://composio.dev)*

REQUIRED CONTEXT

  • Rube MCP connection
  • active Blocknative connection via RUBE_MANAGE_CONNECTIONS

OPTIONAL CONTEXT

  • session_id
  • specific use_case for tool search

TOOLS REQUIRED

  • RUBE_SEARCH_TOOLS
  • RUBE_MANAGE_CONNECTIONS
  • RUBE_MULTI_EXECUTE_TOOL
  • RUBE_GET_TOOL_SCHEMAS
  • RUBE_REMOTE_WORKBENCH

ROLES & RULES

  1. Always search tools first for current schemas
  2. Always call RUBE_SEARCH_TOOLS first to get current tool schemas
  3. Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
  4. Call RUBE_MANAGE_CONNECTIONS with toolkit blocknative
  5. If connection is not ACTIVE, follow the returned auth link to complete setup
  6. Confirm connection status shows ACTIVE before running any workflows
  7. Always discover available tools before executing workflows
  8. Never hardcode tool slugs or arguments without calling RUBE_SEARCH_TOOLS
  9. Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE status before executing tools
  10. Use exact field names and types from the search results
  11. Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty
  12. Reuse session IDs within a workflow
  13. Generate new ones for new workflows
  14. Check responses for pagination tokens and continue fetching until complete

EXPECTED OUTPUT

Format
markdown
Constraints
  • always call RUBE_SEARCH_TOOLS first
  • verify ACTIVE connection status before execution
  • use exact schemas from search results
  • include memory parameter even if empty

SUCCESS CRITERIA

  • Verify Rube MCP connection
  • Confirm ACTIVE Blocknative connection
  • Discover tools via RUBE_SEARCH_TOOLS before execution
  • Use schema-compliant arguments
  • Include memory parameter in executions

FAILURE MODES

  • Hardcode tool slugs without searching first
  • Skip connection status verification
  • Omit memory parameter in tool execution
  • Ignore pagination tokens

CAVEATS

Dependencies
  • RUBE_SEARCH_TOOLS available
  • RUBE_MANAGE_CONNECTIONS with toolkit blocknative
  • Active Blocknative connection
Missing context
  • Target client or MCP host environment
  • Error handling or retry strategy for failed tool calls
Ambiguities
  • Placeholder text "your specific Blocknative task" left in example without clear substitution guidance
  • Tool call examples shown as pseudo-YAML blocks rather than precise argument syntax

QUALITY

OVERALL
0.81
CLARITY
0.82
SPECIFICITY
0.88
REUSABILITY
0.78
COMPLETENESS
0.85

IMPROVEMENT SUGGESTIONS

  • Replace inline placeholders with explicit {{use_case}} style variables and add a short usage example
  • Add a minimal complete end-to-end example call sequence with realistic values

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.

MORE FOR AGENT