AI SQL Agent Queries n8n Credentials

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 →

{
  "nodes": [
    {
      "id": "382dddd4-da50-49fa-90a2-f7d6d160afdf",
      "name": "When clicking \"Test workflow\"",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        920,
        280
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "efa8f415-62f7-43b3-a76a-a2eabf779cb8",
      "name": "Map Workflows & Credentials",
      "type": "n8n-nodes-base.set",
      "position": [
        1360,
        280
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "0fd19a68-c561-4cc2-94d6-39848977e6d2",
              "name": "workflow_id",
              "type": "string",
              "value": "={{ $json.id }}"
            },
            {
              "id": "a81f9e6f-9c78-4c3d-9b79-e820f8c5ba29",
              "name": "workflow_name",
              "type": "string",
              "value": "={{ $json.name }}"
            },
            {
              "id": "58ab0f2f-7598-48de-bea1-f3373c5731fe",
              "name": "credentials",
              "type": "array",
              "value": "={{ $json.nodes.map(node => node.credentials).compact().reduce((acc,cred) => { const keys = Object.keys(cred); const items = keys.map(key => ({ type: key, ...cred[key] })); acc.push(...items); return acc; }, []) }}"
            }
          ]
        }
      },
      "typeVersion": 3.3
    },
    {
      "id": "9e9b4f9c-12b7-47ba-8cf4-a9818902a538",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1084,
        252
      ],
      "parameters": {
        "width": 216,
        "height": 299.56273929030715,
        "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n### \ud83d\udea8Required\nYou'll need an n8n API key. Note: available workflows will be scoped to your key."
      },
      "typeVersion": 1
    },
    {
      "id": "cf04eff5-12b2-42fb-9089-2d0c992af1b8",
      "name": "Save to Database",
      "type": "n8n-nodes-base.code",
      "position": [
        1540,
        280
      ],
      "parameters": {
        "language": "python",
        "pythonCode": "import json\nimport sqlite3\ncon = sqlite3.connect(\"n8n_workflow_credentials.db\")\n\ncur = con.cursor()\ncur.execute(\"CREATE TABLE IF NOT EXISTS n8n_workflow_credentials (workflow_id TEXT PRIMARY KEY, workflow_name TEXT, credentials TEXT);\")\n\nfor item in _input.all():\n cur.execute('INSERT OR REPLACE INTO n8n_workflow_credentials VALUES(?,?,?)', (\n item.json.workflow_id,\n item.json.workflow_name,\n json.dumps(item.json.credentials.to_py())\n ))\n\ncon.commit()\ncon.close()\n\nreturn [{ \"affected_rows\": len(_input.all()) }]"
      },
      "typeVersion": 2
    },
    {
      "id": "7e32cf83-0498-4666-8677-7fd32eec779c",
      "name": "Chat Trigger",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        1880,
        280
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "8c37f2ae-192b-4f98-a6fa-5aabf870e9e0",
      "name": "Query Workflow Credentials Database",
      "type": "@n8n/n8n-nodes-langchain.toolCode",
      "position": [
        2320,
        440
      ],
      "parameters": {
        "name": "query_workflow_credentials_database",
        "language": "python",
        "pythonCode": "import json\nimport sqlite3\ncon = sqlite3.connect(\"n8n_workflow_credentials.db\")\n\ncur = con.cursor()\nres = cur.execute(query);\n\noutput = json.dumps(res.fetchall())\n\ncon.close()\nreturn output;",
        "description": "Call this tool to query the workflow credentials database. The database is already set. The available tables are as follows:\n* n8n_workflow_credentials (workflow_id TEXT PRIMARY KEY, workflow_name TEXT, credentials TEXT);\n * n8n_workflow_credentials.credentials are stored as json string and the app name may be obscured. Prefer querying using the %LIKE% operation for best results.\n\nPass a SQL SELECT query to this tool for the available tables."
      },
      "typeVersion": 1.1
    },
    {
      "id": "60b2ab16-dc7c-4cb8-a58f-696f721b8d6f",
      "name": "OpenAI Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        2060,
        440
      ],
      "parameters": {
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "adf576c1-ddb0-4fef-980c-5b485a3204f2",
      "name": "Window Buffer Memory",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "position": [
        2180,
        440
      ],
      "parameters": {},
      "typeVersion": 1.2
    },
    {
      "id": "4335b038-3e9f-4173-986d-cabdb87cc0b4",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        860,
        100
      ],
      "parameters": {
        "color": 7,
        "width": 930.8402221561373,
        "height": 488.8805508857059,
        "content": "## Step 1. Store Workflows Credential Mappings to Database\n\nWe'll achieve this by querying n8n's built-in API to query all workflows, extract the credentials list from the nodes within and then store them in a SQLite database. Don't worry, the actual credential data won't be exposed! For the database, we'll abuse the fact that the code node is able to create Sqlite databases - however, this is created in memory and will be wiped if the n8n instance is restarted."
      },
      "typeVersion": 1
    },
    {
      "id": "c1f557ee-1176-4f3e-8431-d162f1a59990",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1820,
        100
      ],
      "parameters": {
        "color": 7,
        "width": 688.6507290693205,
        "height": 527.3794193342486,
        "content": "## Step 2. Use Agent as Search Interface\n\nInstead of building a form interface like a regular person, we'll just use an AI tools agent who is given aaccess to perform queries on our database. You can ask it things like \"which workflows are using slack + airtable + googlesheets?\""
      },
      "typeVersion": 1
    },
    {
      "id": "9bdc3fa9-d4a0-4040-bb32-6c76aaca3ad9",
      "name": "Workflow Credentials Helper Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        2080,
        280
      ],
      "parameters": {
        "options": {
          "systemMessage": "=You help find information on n8n workflow credentials. When user mentions an app, assume they mean the workflow credential for the app.\n* Only if the user requests to provide a link to the workflow, replace $workflow_id with the workflow id in the following url schema: {{ window.location.protocol + '//' + window.location.host }}/workflow/$workflow_id"
        }
      },
      "typeVersion": 1.6
    },
    {
      "id": "ff39f504-9953-47c9-81eb-3146dfd6c8c5",
      "name": "Sticky Note4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        420,
        100
      ],
      "parameters": {
        "width": 415.13049730628427,
        "height": 347.7398931123371,
        "content": "## Try It Out!\n\n### This workflow let's you query workflow credentials using an AI SQL agent. Example use-case could be:\n* \"Which workflows are using Slack and Google Calendar?\"\n* \"Which workflows have AI in their name but are not using openAI?\"\n\n### Run the Steps separately!\n* Step 1 populates a local database\n* Step 2 engages with the chatbot"
      },
      "typeVersion": 1
    },
    {
      "id": "3db2116c-abde-4856-bd1e-a15e0275477f",
      "name": "n8n",
      "type": "n8n-nodes-base.n8n",
      "position": [
        1140,
        280
      ],
      "parameters": {
        "filters": {},
        "requestOptions": {}
      },
      "credentials": {
        "n8nApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1
    }
  ],
  "connections": {
    "n8n": {
      "main": [
        [
          {
            "node": "Map Workflows & Credentials",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Chat Trigger": {
      "main": [
        [
          {
            "node": "Workflow Credentials Helper Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Workflow Credentials Helper Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Window Buffer Memory": {
      "ai_memory": [
        [
          {
            "node": "Workflow Credentials Helper Agent",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "Map Workflows & Credentials": {
      "main": [
        [
          {
            "node": "Save to Database",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When clicking \"Test workflow\"": {
      "main": [
        [
          {
            "node": "n8n",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Query Workflow Credentials Database": {
      "ai_tool": [
        [
          {
            "node": "Workflow Credentials Helper Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    }
  }
}

Credentials you'll need

Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.

• n8nApi
• openAiApi

How this works

This workflow empowers n8n users to effortlessly query and retrieve their stored credentials using an AI-powered SQL agent, saving hours of manual searching through complex setups. It's ideal for workflow builders and administrators who need quick insights into credential details without disrupting their automation flow. The key step involves the AI agent interfacing with n8n's internal database via the toolCode node, combined with OpenAI's chat model for natural language queries, ensuring accurate and context-aware responses.

Use this workflow when managing multiple n8n instances and frequently auditing credentials for security or optimisation, especially in team environments where verbal queries streamline collaboration. Avoid it for simple credential lookups that don't require AI interpretation, or if your n8n setup lacks database access enabled. Common variations include adapting the agent for querying other n8n entities like workflows or executions, or integrating with external databases for broader data exploration.

About this workflow

Query N8N Credentials With Ai Sql Agent. Uses manualTrigger, stickyNote, chatTrigger, toolCode. Event-driven trigger; 13 nodes.

Source: https://github.com/Zie619/n8n-workflows — 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.