Mud Player 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": "MUD Player Agent",
  "nodes": [
    {
      "parameters": {
        "httpMethod": "POST",
        "path": "player-action",
        "responseMode": "onReceived",
        "options": {}
      },
      "id": "webhook-trigger",
      "name": "Player Action Webhook",
      "type": "n8n-nodes-base.webhook",
      "typeVersion": 1,
      "position": [
        240,
        300
      ]
    },
    {
      "parameters": {
        "functionCode": "// Extract player action from webhook\nconst action = $input.first().json;\nconst playerId = $env.PLAYER_ID || 'player1';\nconst characterName = $env.CHARACTER_NAME || 'Unknown';\nconst characterClass = $env.CHARACTER_CLASS || 'warrior';\n\n// Determine action type\nlet mcpAction = {};\n\nif (action.type === 'create_character') {\n  mcpAction = {\n    tool: 'create_character',\n    parameters: {\n      player_id: playerId,\n      name: characterName,\n      character_class: characterClass\n    }\n  };\n} else if (action.type === 'move') {\n  mcpAction = {\n    tool: 'move_character',\n    parameters: {\n      player_id: playerId,\n      direction: action.direction || 'north'\n    }\n  };\n} else if (action.type === 'examine') {\n  mcpAction = {\n    tool: 'examine_object',\n    parameters: {\n      player_id: playerId,\n      target: action.target || 'room'\n    }\n  };\n} else if (action.type === 'skill_check') {\n  mcpAction = {\n    tool: 'attempt_skill_check',\n    parameters: {\n      player_id: playerId,\n      skill_type: action.skill_type || 'strength',\n      target: action.target\n    }\n  };\n} else if (action.type === 'rest') {\n  mcpAction = {\n    tool: 'rest_character',\n    parameters: {\n      player_id: playerId\n    }\n  };\n} else if (action.type === 'status') {\n  mcpAction = {\n    tool: 'get_character_status',\n    parameters: {\n      player_id: playerId\n    }\n  };\n} else {\n  // Default to getting status\n  mcpAction = {\n    tool: 'get_character_status',\n    parameters: {\n      player_id: playerId\n    }\n  };\n}\n\nreturn {\n  json: {\n    action: mcpAction,\n    playerId: playerId,\n    originalAction: action\n  }\n};"
      },
      "id": "action-parser",
      "name": "Parse Player Action",
      "type": "n8n-nodes-base.function",
      "typeVersion": 1,
      "position": [
        460,
        300
      ]
    },
    {
      "parameters": {
        "url": "http://mcp-mud-server:8080/mcp",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Content-Type",
              "value": "application/json"
            }
          ]
        },
        "sendBody": true,
        "bodyParameters": {
          "parameters": [
            {
              "name": "method",
              "value": "tools/call"
            },
            {
              "name": "params",
              "value": "={{ $json.action }}"
            }
          ]
        },
        "options": {}
      },
      "id": "mcp-call",
      "name": "Call MCP Tool",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.1,
      "position": [
        680,
        300
      ]
    },
    {
      "parameters": {
        "functionCode": "// Process MCP response and format for output\nconst mcpResponse = $input.first().json;\nconst originalAction = $node['Parse Player Action'].json.originalAction;\nconst playerId = $node['Parse Player Action'].json.playerId;\n\n// Extract result from MCP response\nlet result = {};\nif (mcpResponse.result && mcpResponse.result.content) {\n  try {\n    result = JSON.parse(mcpResponse.result.content[0].text);\n  } catch (e) {\n    result = { success: false, error: 'Failed to parse MCP response' };\n  }\n} else {\n  result = { success: false, error: 'No response from MCP server' };\n}\n\n// Format response for the player\nlet formattedResponse = {\n  playerId: playerId,\n  action: originalAction.type,\n  success: result.success,\n  timestamp: new Date().toISOString()\n};\n\nif (result.success) {\n  formattedResponse.message = result.message || 'Action completed successfully';\n  formattedResponse.data = result;\n} else {\n  formattedResponse.error = result.error || 'Unknown error occurred';\n}\n\n// Add specific formatting for different action types\nif (originalAction.type === 'status' && result.character_data) {\n  formattedResponse.characterStatus = {\n    name: result.character_data.name,\n    class: result.character_data.class,\n    level: result.character_data.level,\n    health: result.character_data.health,\n    mana: result.character_data.mana,\n    location: result.character_data.location\n  };\n} else if (originalAction.type === 'move' && result.room_description) {\n  formattedResponse.roomDescription = result.room_description;\n} else if (originalAction.type === 'examine' && result.description) {\n  formattedResponse.description = result.description;\n} else if (originalAction.type === 'skill_check' && result.skill_check_result) {\n  formattedResponse.skillResult = {\n    success: result.skill_check_result.success,\n    total: result.skill_check_result.total,\n    roll: result.skill_check_result.roll,\n    successLevel: result.skill_check_result.success_level\n  };\n}\n\nreturn { json: formattedResponse };"
      },
      "id": "response-formatter",
      "name": "Format Response",
      "type": "n8n-nodes-base.function",
      "typeVersion": 1,
      "position": [
        900,
        300
      ]
    },
    {
      "parameters": {
        "respondWith": "json",
        "responseBody": "={{ $json }}"
      },
      "id": "webhook-response",
      "name": "Send Response",
      "type": "n8n-nodes-base.respondToWebhook",
      "typeVersion": 1,
      "position": [
        1120,
        300
      ]
    },
    {
      "parameters": {
        "url": "http://ollama:11434/api/generate",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Content-Type",
              "value": "application/json"
            }
          ]
        },
        "sendBody": true,
        "bodyParameters": {
          "parameters": [
            {
              "name": "model",
              "value": "llama3.2"
            },
            {
              "name": "prompt",
              "value": "You are playing a character named {{ $env.CHARACTER_NAME }} ({{ $env.CHARACTER_CLASS }}) in a text-based dungeon adventure game. Based on the current game state, decide what action to take next. Current status: {{ $json.data }}. Respond with a JSON object containing your next action, like: {\"type\": \"move\", \"direction\": \"north\"} or {\"type\": \"examine\", \"target\": \"door\"} or {\"type\": \"skill_check\", \"skill_type\": \"strength\", \"target\": \"door\"}."
            },
            {
              "name": "stream",
              "value": false
            }
          ]
        }
      },
      "id": "ai-decision",
      "name": "AI Decision Making",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.1,
      "position": [
        900,
        500
      ]
    }
  ],
  "connections": {
    "Player Action Webhook": {
      "main": [
        [
          {
            "node": "Parse Player Action",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Parse Player Action": {
      "main": [
        [
          {
            "node": "Call MCP Tool",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Call MCP Tool": {
      "main": [
        [
          {
            "node": "Format Response",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Format Response": {
      "main": [
        [
          {
            "node": "Send Response",
            "type": "main",
            "index": 0
          },
          {
            "node": "AI Decision Making",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": true,
  "settings": {},
  "createdAt": "2024-01-01T00:00:00.000Z",
  "updatedAt": "2024-01-01T00:00:00.000Z",
  "id": "player-agent-workflow"
}

About this workflow

MUD Player Agent. Uses httpRequest. Webhook trigger; 6 nodes.

Source: https://github.com/sbaumgartner/MCP-Game/blob/cf4e4706437b3216416e269990fad73bf2eaf45c/workflows/player-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.