Chat API

The Chat API enables real-time conversations with AI agents for analytics and data exploration.

The Chat API is available in Cube Cloud on Premium and above (opens in a new tab) product tiers.

Endpoint

https://ai-engineer.cubecloud.dev/api/v1/public/{tenantName}/agents/{agentId}/chat/stream-chat-state

Overview

The Chat API enables real-time streaming conversations with Cube's AI agents. This endpoint allows applications to integrate AI-powered analytics conversations directly into their user interfaces.

Authentication

Use the session-based authentication flow:

Generate a session using your API key. This endpoint will automatically create (insert) or update the external user based on the externalId provided:

Accounts are limited to 10,000 external users. To increase this limit, please contact support.

const session = await fetch('https://your-tenant.cubecloud.dev/api/v1/embed/generate-session', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Api-Key ${API_KEY}',
  },
  body: JSON.stringify({ 
    externalId: 'user@example.com',
    userAttributes: [ // optional
      {
        name: 'city',
        value: 'San Francisco'
      }
    ]
  }),
});
 
const { sessionId } = await session.json();

Exchange session ID for a token:

const tokenResponse = await fetch('https://your-tenant.cubecloud.dev/api/v1/embed/session/token', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Api-Key ${API_KEY}',
  },
  body: JSON.stringify({ sessionId }),
});
 
const { token } = await tokenResponse.json();

User Attributes

User attributes allow you to pass contextual information about the user to the AI agent. This enables personalized responses and automatic data filtering based on user permissions through row-level security policies.

User attributes must first be configured in your Cube admin panel before they can be used. See the User Attributes Administration Guide for setup instructions.

Supported Fields:

externalId (required): Unique identifier for the user
email (optional): User's email address
userAttributes (optional): Array of key-value pairs containing user metadata

User Attribute Structure:

{
  name: 'string',    // Must match an attribute name configured in admin panel
  value: 'string'    // Attribute value (e.g., 'San Francisco', 'Engineering')
}

How User Attributes Work:

Row-Level Security: Automatically filter data based on user attributes through access policies
Personalized Responses: AI agent can tailor responses based on user context
Access Control: Restrict data access to only what the user should see

Example Use Cases:

Filter sales data by user's assigned territory
Show only customers from user's city
Limit financial data based on user's department
Personalize dashboards by user role

The attributes passed during session generation become available in the security context as securityContext.cubeCloud.userAttributes.{attributeName} for use in access policies.

Endpoint Reference

POST /api/v1/public/{tenantName}/agents/{agentId}/chat/stream-chat-state

Base URL: https://ai-engineer.cubecloud.dev

Path Parameters

tenantName (string, required): The tenant identifier (e.g., "acme"). It is in your account URL, e.g. https://acme.cubecloud.dev (opens in a new tab)
agentId (string, required): The AI agent identifier (e.g., "1"). You can find it in Admin → Agents → Click on Agent row in the table.

Request Body

chatId (string, required): Unique identifier for the chat session. We recommend generating a UUID for this.
input (string): User message or query to send to the AI agent, e.g. "What is our revenue last month?"

Response Format

The API returns streaming JSON responses. Each line contains a separate JSON object representing a chat message or state update.

Response Fields

id (string): Unique message identifier
role (string): Message sender: "user" or "assistant"
content (string): Message content (streamed incrementally for assistant messages)
thinking (string): Agent's internal reasoning process (visible in development mode)
toolCall (object): Information about tool calls made by the agent during processing
- name (string): Name of the tool being called
- input (string): JSON string containing the input parameters for the tool
- result (string): JSON string containing the tool's response (only present when tool call is complete)
isDelta (boolean): Whether this is an incremental content update
isInProcess (boolean): Whether the message is still being generated
sort (number): Message ordering sequence number
state (object): Current streaming state information

Response Examples

The API returns a series of JSON objects, each on a separate line. Here's what a typical conversation looks like:

Initial State Message:

{
  "id": "__cutoff__",
  "role": "assistant",
  "state": {
    "isStreaming": false
  },
  "sort": 0
}

User Message Echo:

{
  "id": "1732512345678-message",
  "role": "user",
  "content": "Show me revenue trends for the last 6 months",
  "isDelta": false,
  "sort": 1
}

Assistant Response Start:

{
  "id": "cdfe1a84-08d7-40b9-8b1c-e7e3a698647e",
  "role": "assistant",
  "content": "",
  "thinking": "",
  "graphPath": ["cube_data_analyst_agent"],
  "isStructuredResponse": false,
  "isInProcess": true,
  "isDelta": true,
  "sort": 2
}

Thinking Process:

{
  "id": "cdfe1a84-08d7-40b9-8b1c-e7e3a698647e",
  "role": "assistant",
  "content": "",
  "thinking": "The user wants to see revenue trends for the last 6 months. I need to query the revenue data and create a visualization.",
  "graphPath": ["cube_data_analyst_agent"],
  "isStructuredResponse": false,
  "isInProcess": true,
  "isDelta": true,
  "sort": 3
}

Content Streaming:

{
  "id": "cdfe1a84-08d7-40b9-8b1c-e7e3a698647e",
  "role": "assistant",
  "content": "I'll help you analyze revenue trends for the last 6 months. Let me query the data and create a visualization.",
  "thinking": "",
  "graphPath": ["cube_data_analyst_agent"],
  "isStructuredResponse": false,
  "isInProcess": true,
  "isDelta": true,
  "sort": 4
}

Tool Call Initiated:

{
  "id": "4849adb2-b55d-4afe-946b-fc117bcadaf5",
  "role": "assistant",
  "toolCall": {
    "name": "cubeMeta",
    "input": "{\"searchQuery\":\"revenue trends\"}"
  },
  "isInProcess": true,
  "graphPath": ["cube_data_analyst_agent", "tools"],
  "isStructuredResponse": false,
  "isDelta": false,
  "sort": 5
}

Tool Call Result:

{
  "id": "4849adb2-b55d-4afe-946b-fc117bcadaf5",
  "role": "assistant",
  "toolCall": {
    "name": "cubeMeta",
    "input": "{\"searchQuery\":\"revenue trends\"}",
    "result": "{\"cubes\":[{\"name\":\"Revenue\",\"measures\":[\"Revenue.totalRevenue\",\"Revenue.monthlyGrowth\"]}]}"
  },
  "isInProcess": false,
  "graphPath": ["cube_data_analyst_agent", "tools"],
  "isStructuredResponse": false,
  "isDelta": false,
  "sort": 6
}

SQL Query Tool Call:

{
  "id": "a1b2c3d4-e5f6-7890-ab12-cd34ef567890",
  "role": "assistant",
  "toolCall": {
    "name": "cubeSqlApi",
    "input": "{\"query\":\"SELECT Revenue.totalRevenue, Revenue.month FROM Revenue WHERE Revenue.dateRange BETWEEN '2024-01-01' AND '2024-06-30' ORDER BY Revenue.month\"}"
  },
  "isInProcess": true,
  "graphPath": ["cube_data_analyst_agent", "tools"],
  "isStructuredResponse": false,
  "isDelta": false,
  "sort": 7
}

SQL Query Result:

{
  "id": "a1b2c3d4-e5f6-7890-ab12-cd34ef567890",
  "role": "assistant",
  "toolCall": {
    "name": "cubeSqlApi",
    "input": "{\"query\":\"SELECT Revenue.totalRevenue, Revenue.month FROM Revenue WHERE Revenue.dateRange BETWEEN '2024-01-01' AND '2024-06-30' ORDER BY Revenue.month\"}",
    "result": "{\"data\":[{\"Revenue.totalRevenue\":1800000,\"Revenue.month\":\"2024-01\"},{\"Revenue.totalRevenue\":1950000,\"Revenue.month\":\"2024-02\"},{\"Revenue.totalRevenue\":2300000,\"Revenue.month\":\"2024-03\"},{\"Revenue.totalRevenue\":2100000,\"Revenue.month\":\"2024-04\"},{\"Revenue.totalRevenue\":2250000,\"Revenue.month\":\"2024-05\"},{\"Revenue.totalRevenue\":2400000,\"Revenue.month\":\"2024-06\"}],\"annotation\":{\"measures\":{\"Revenue.totalRevenue\":{\"title\":\"Total Revenue\",\"type\":\"number\"}},\"dimensions\":{\"Revenue.month\":{\"title\":\"Month\",\"type\":\"time\"}}}}"
  },
  "isInProcess": false,
  "graphPath": ["cube_data_analyst_agent", "tools"],
  "isStructuredResponse": false,
  "isDelta": false,
  "sort": 8
}

Final Complete Message:

{
  "id": "cdfe1a84-08d7-40b9-8b1c-e7e3a698647e",
  "role": "assistant",
  "content": "I'll help you analyze revenue trends for the last 6 months. Let me query the data and create a visualization.\n\nBased on your revenue data, here are the key trends:\n\n📈 **Overall Growth**: 15% increase over the 6-month period\n💰 **Peak Month**: March 2024 with $2.3M revenue\n📊 **Steady Growth**: Consistent month-over-month growth of 2-3%\n\nWould you like me to break this down by product category or region?",
  "thinking": "",
  "graphPath": ["cube_data_analyst_agent"],
  "isStructuredResponse": false,
  "isInProcess": false,
  "isDelta": false,
  "sort": 9
}

Final State Update:

{
  "id": "__state__",
  "role": "assistant",
  "state": {
    "messages": [{
      "lc": 1,
      "type": "constructor",
      "id": ["langchain_core", "messages", "HumanMessage"],
      "kwargs": {
        "content": "Show me revenue trends for the last 6 months"
      }
    }]
  },
  "isDelta": false,
  "sort": 10
}

Tool Calls

When the AI agent performs actions like querying data or searching metadata, tool calls are included in the response stream. These provide transparency into the agent's reasoning and data retrieval process.

All tool results are returned as JSON strings within the toolCall.result field, not as parsed JSON objects. You must parse these strings to access the structured data.

Key Points:

toolCall.input - JSON string containing tool parameters
toolCall.result - JSON string containing tool response (only present when isInProcess: false)
Both input and result contain escaped JSON that requires parsing
Results may contain nested JSON structures, especially for complex data queries
Error responses are also JSON strings with consistent error formatting

Parsing Example:

// Parse the tool result JSON string
const toolResult = JSON.parse(message.toolCall.result);
 
if (toolResult.error) {
  console.error('Tool error:', toolResult.error);
} else {
  // Handle successful result based on tool type
  if (message.toolCall.name === 'cubeSqlApi') {
    const data = toolResult.data;
    const annotation = toolResult.annotation;
    // Process query results...
  }
}

cubeMeta

Searches cube metadata and schema information

The cubeMeta tool returns cube schema information as a JSON string. When successful, the result contains:

{
  "toolCall": {
    "name": "cubeMeta",
    "input": "...",
    "result": "..."
  }
}

Input Structure:

{
  "searchQuery": "sales pipeline revenue"
}

Input Fields:

searchQuery (string): Search query for data model

Result Structure:

{
  "cubes": [
    {
      "name": "sales_pipeline_view",
      "type": "view",
      "title": "Sales Pipeline View",
      "members": [
        {
          "name": "sales_pipeline_view.company_name",
          "title": "Company Name",
          "description": "Name of the company/prospect",
          "type": "string"
        },
        {
          "name": "sales_pipeline_view.deal_amount",
          "title": "Deal Amount",
          "description": "Total deal value",
          "type": "number"
        },
        {
          "name": "sales_pipeline_view.stage",
          "title": "Sales Stage",
          "description": "Current stage of the deal (Lead, Demo, Negotiation, Won, Lost, etc.)",
          "type": "string"
        },
        {
          "name": "sales_pipeline_view.count",
          "title": "Deal Count",
          "description": "Total number of deals",
          "type": "number",
          "aggType": "count"
        }
      ]
    },
    {
      "name": "revenue_view",
      "type": "view",
      "title": "Revenue View",
      "members": [
        {
          "name": "revenue_view.total_amount",
          "title": "Total Revenue",
          "description": "Sum of all revenue",
          "type": "number",
          "aggType": "sum"
        },
        {
          "name": "revenue_view.month",
          "title": "Revenue Month",
          "description": "Month of revenue recognition",
          "type": "time"
        },
        {
          "name": "revenue_view.is_recurring",
          "title": "Is Recurring Revenue",
          "description": "Whether this is recurring or one-time revenue",
          "type": "boolean"
        }
      ]
    }
  ],
  "searchQuery": "sales pipeline revenue"
}

Result Fields:

cubes (array): Available cube/view definitions with members
searchQuery (string): The original search query used

cubeSqlApi

Executes SQL queries against cube data

The cubeSqlApi tool executes SQL queries and returns data with metadata. The input typically includes additional context fields:

{
  "toolCall": {
    "name": "cubeSqlApi",
    "input": "...",
    "result": "..."
  }
}

Input Structure:

{
  "sqlQuery": "SELECT deals_view.company_name, deals_view.deal_name FROM deals_view WHERE deals_view.stage = 'Negotiation' LIMIT 10",
  "queryTitle": "Sales Pipeline Overview",
  "description": "Retrieving deal information from the deals view for current negotiations",
  "userRequest": "show me current deals in negotiation",
  "memoryId": "a1b2c3d4-5e6f-7g8h-9i0j-k1l2m3n4o5p6",
  "vegaSpec": "vega lite v5 visualization spec as JSON string"
}

Input Fields:

sqlQuery (string): The SQL query to execute
queryTitle (string): Human-readable title for the query
description (string): Detailed description of what the query does
userRequest (string): Original user request that triggered this query
memoryId (string): Reference to previous analysis or context
vegaSpec (string): Vega-Lite v5 visualization specification as JSON string (when visualization is generated)

Result Structure:

{
  "sqlQuery": "SELECT deals_view.company_name, deals_view.name AS deal_name...",
  "queryTitle": "Current Deals Overview",
  "description": "Retrieving deals showing company names, deal names, stages...",
  "userRequest": "show me deals",
  "schema": [
    {
      "name": "company_name",
      "column_type": "String"
    },
    {
      "name": "deal_name", 
      "column_type": "String"
    },
    {
      "name": "stage",
      "column_type": "String"
    },
    {
      "name": "tenant_name",
      "column_type": "String"
    },
    {
      "name": "activity_score",
      "column_type": "Double"
    },
    {
      "name": "deal_count",
      "column_type": "Int64"
    }
  ],
  "data": [
    ["Acme Corp", "Enterprise Solution", "Negotiation", "acme-workspace", "245", "1"],
    ["Beta Industries", "Analytics Platform", "Testing", "beta-analytics", "189", "1"],
    ["Gamma LLC", "Data Pipeline", "Demo", "gamma-data", "156", "1"]
  ],
  "totalRows": 25,
  "uuid": "a1b2c3d4-5e6f-7g8h-9i0j-k1l2m3n4o5p6",
  "vegaSpec": "vega lite v5 visualization spec as JSON string"
}

Result Fields:

sqlQuery (string): The executed SQL query
queryTitle (string): Human-readable title for the query
description (string): Detailed description of what the query does
userRequest (string): Original user request that triggered this query
schema (array): Column definitions with name and column_type for each field
data (array): Query result rows as arrays of values
totalRows (number): Total number of rows returned
uuid (string): Unique identifier for this query result
vegaSpec (string): Vega-Lite v5 visualization specification as JSON string (when visualization is generated)

Loading all Results

Query results in cubeSqlApi toolCall.result.data are limited to 100 rows by default. Use totalRows to check if more data is available.

If you need to load all the data, you need to use sqlQuery from the results to make a call to the Cube API.

Displaying charts

The cubeSqlApi tool call returns vegaSpec that can be used to display data.

Note that it doesn't contain data. You need to use the data from toolCall.result.data.

Styling charts

When rendering Vega charts, you can apply custom styling to match the look and feel of your application. This includes adjusting colors, fonts, and other visual elements.

Here's a configuration example that mimics Cube's default styling:

{
  // Your Vega configuration
 
  "config": {
    "background": "#ffffff",
    "padding": 16,
    "view": {
      "stroke": "transparent"
    },
    "axis": {
      "domainColor": "#E0E0E0",
      "gridColor": "#F5F5F5",
      "grid": true,
      "labelFont": "Inter, sans-serif",
      "labelFontSize": 12,
      "labelColor": "#43436B",
      "titleFont": "Inter, sans-serif",
      "titleFontSize": 12,
      "titleColor": "#43436B",
      "titlePadding": 8
    },
    "numberFormat": "s",
    "timeFormat": "%Y-%m",
    "format": {
      "number": {
        "format": "s",
        "formatType": "number"
      },
      "time": {
        "format": "%Y-%m",
        "formatType": "time"
      }
    },
    "legend": {
      "labelFont": "Inter, sans-serif",
      "titleFont": "Inter, sans-serif",
      "labelColor": "#43436B",
      "titleColor": "#43436B",
      "labelFontSize": 12,
      "titleFontSize": 12,
      "titlePadding": 8,
      "padding": 8
    },
    "line": {
      "strokeWidth": 3,
      "strokeCap": "round",
      "point": true
    },
    "text": {
      "color": "#43436B"
    },
    "point": {
      "filled": true,
      "size": 60
    },
    "range": {
      "category": [
        "#4E79A7",
        "#F28E2B",
        "#E15759",
        "#76B7B2",
        "#59A14F",
        "#EDC948",
        "#B07AA1",
        "#FF9DA7",
        "#9C755F",
        "#BAB0AC"
      ],
      "heatmap": [
        "#eff6ff",
        "#1e40af"
      ]
    },
    "scale": {
      "band": {
        "padding": 0.1,
        "round": true
      },
      "linear": {
        "nice": true,
        "zero": true
      },
      "ordinal": {
        "type": "band",
        "padding": 0.1
      },
      "time": {
        "type": "utc",
        "nice": true
      },
      "log": {
        "base": 10,
        "domain": {
          "data": "table",
          "field": "x"
        },
        "range": {
          "data": "table",
          "field": "y"
        }
      },
      "range": [
        "#4E79A7",
        "#F28E2B"
      ]
    }
  }
}

Error Handling

When a tool encounters an error, the result field contains structured error information as a JSON string:

Standard Error Format:

When an error occurs, the result property of the toolCall will contain an error property.

{
  "toolCall": {
    "name": "cubeMeta",
    "input": "{\"searchQuery\":\"opportunities deals\"}",
    "result": "{\n  \"error\": \"Error: BadRequestError: Bad branch\"\n}"
  },
  "isInProcess": false
}

Code Examples

Python

Bash

JavaScript

Error Handling

401 Unauthorized: Invalid or missing JWT token. Verify your token is properly signed and not expired.
400 Bad Request: Invalid request body or parameters. Check required fields and data types.
404 Not Found: Agent or tenant not found. Verify the tenantName and agentId parameters.
500 Internal Server Error: Server processing error. Contact support if the issue persists.

Embedding MCP server