Orion Mcp — AI Agent Expert Committee

The workflow JSON

Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →

{
  "name": "Orion MCP \u2014 AI Agent Expert Committee",
  "nodes": [
    {
      "parameters": {
        "httpMethod": "POST",
        "path": "trading-signal-ai",
        "responseMode": "lastNode",
        "options": {}
      },
      "id": "webhook-in",
      "name": "Webhook (Java Bot Signal)",
      "type": "n8n-nodes-base.webhook",
      "typeVersion": 2,
      "position": [
        250,
        300
      ]
    },
    {
      "parameters": {
        "agent": "conversationalAgent",
        "promptType": "define",
        "text": "You are a trading decision coordinator for Step Index. Analyze this trading signal using the Orion expert tools:\n\n{{ JSON.stringify($json, null, 2) }}\n\nCall the consult_committee tool with all the parameters from the signal. Then interpret the results and provide your final recommendation in this JSON format:\n{\n  \"action\": \"EXECUTE\" or \"REJECT\" or \"WAIT\",\n  \"confidence\": 0.0-1.0,\n  \"reasoning\": \"your analysis\"\n}",
        "options": {
          "systemMessage": "You are an expert trading analyst. Use the Orion tools to validate signals. Be conservative \u2014 when in doubt, reject."
        }
      },
      "id": "ai-agent",
      "name": "AI Agent (Decision Maker)",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 1.7,
      "position": [
        500,
        300
      ]
    },
    {
      "parameters": {
        "toolType": "mcpClient",
        "mcpConfig": {
          "transport": "streamableHttp",
          "url": "http://orion-consultant:8100/mcp/"
        }
      },
      "id": "mcp-orion",
      "name": "Orion MCP Tools",
      "type": "@n8n/n8n-nodes-langchain.toolMcp",
      "typeVersion": 1,
      "position": [
        500,
        500
      ]
    },
    {
      "parameters": {
        "model": "gpt-4o-mini",
        "options": {
          "temperature": 0.1
        }
      },
      "id": "openai-model",
      "name": "OpenAI Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "typeVersion": 1,
      "position": [
        350,
        500
      ]
    }
  ],
  "connections": {
    "Webhook (Java Bot Signal)": {
      "main": [
        [
          {
            "node": "AI Agent (Decision Maker)",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Orion MCP Tools": {
      "ai_tool": [
        [
          {
            "node": "AI Agent (Decision Maker)",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent (Decision Maker)",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    }
  },
  "settings": {
    "executionOrder": "v1"
  },
  "tags": [
    {
      "name": "trading",
      "id": "1"
    },
    {
      "name": "orion-mcp",
      "id": "2"
    },
    {
      "name": "ai-agent",
      "id": "3"
    }
  ]
}

About this workflow

Orion MCP — AI Agent Expert Committee. Uses agent, toolMcp, lmChatOpenAi. Webhook trigger; 4 nodes.

Source: https://github.com/vicbrak2/orion-consultant/blob/5bc8337ad8eff5eed59e4af271faa70a92c273a6/n8n/workflow_mcp_ai_agent.json — original creator credit. Request a take-down →

More AI & RAG workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.