Globiguard Governed Mcp Agent

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": "GlobiGuard governed MCP agent",
  "nodes": [
    {
      "parameters": {
        "options": {}
      },
      "id": "80694f57-c423-4870-b28a-6847e2adddaa",
      "name": "When Chat Message Received",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "typeVersion": 1.1,
      "position": [
        0,
        0
      ]
    },
    {
      "parameters": {
        "options": {
          "systemMessage": "You may use only the tools supplied by the GlobiGuard Governed MCP Gateway. Treat BLOCK, MODIFY, and QUEUE as normal policy outcomes: do not retry around them, do not claim the side effect happened, and explain the next required step. Never invent an ungoverned route to the downstream system."
        }
      },
      "id": "01e45eec-a70c-4310-b4ef-fe4eea9a95a8",
      "name": "Governed AI Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 3.1,
      "position": [
        300,
        0
      ]
    },
    {
      "parameters": {
        "model": {
          "__rl": true,
          "value": "gpt-4.1-mini",
          "mode": "list",
          "cachedResultName": "gpt-4.1-mini"
        },
        "options": {
          "temperature": 0.1
        }
      },
      "id": "341253b7-6a01-49ef-900c-f6438971cfdb",
      "name": "Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "typeVersion": 1.3,
      "position": [
        160,
        220
      ],
      "notes": "Choose and credential the model approved for your environment."
    },
    {
      "parameters": {
        "endpointUrl": "https://mcp.example.com/mcp",
        "serverTransport": "httpStreamable",
        "authentication": "headerAuth",
        "include": "all",
        "options": {
          "timeout": 60000
        }
      },
      "id": "9d794e41-5d42-4d98-9b69-f1c7885af359",
      "name": "GlobiGuard Governed MCP Gateway",
      "type": "@n8n/n8n-nodes-langchain.mcpClientTool",
      "typeVersion": 1.3,
      "position": [
        440,
        220
      ],
      "notes": "Set the HTTPS /mcp URL. Attach an n8n Header Auth credential with Authorization: Bearer <gateway token>. Do not attach the original downstream MCP server to this agent."
    }
  ],
  "connections": {
    "When Chat Message Received": {
      "main": [
        [
          {
            "node": "Governed AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Governed AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "GlobiGuard Governed MCP Gateway": {
      "ai_tool": [
        [
          {
            "node": "Governed AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    }
  },
  "settings": {
    "executionOrder": "v1"
  },
  "staticData": null,
  "tags": [],
  "triggerCount": 0,
  "updatedAt": "2026-07-25T00:00:00.000Z",
  "versionId": "globiguard-governed-mcp-agent-v1"
}

About this workflow

GlobiGuard governed MCP agent. Uses chatTrigger, agent, lmChatOpenAi, mcpClientTool. Chat trigger; 4 nodes.

Source: https://github.com/globiguard/globiguard-open/blob/main/examples/n8n/globiguard-governed-mcp-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.