Skip to main content

Integration with MCP

Introduction​

Tianji MCP Server is a server based on Model Context Protocol (MCP) that serves as a bridge between AI assistants and the Tianji platform. It exposes Tianji platform's survey functionality to AI assistants through the MCP protocol. This server provides the following core features:

  • Query survey results
  • Get detailed survey information
  • Get all surveys in a workspace
  • Get website list

Installation Methods​

NPX Installation​

You can use Tianji MCP Server by adding the following configuration to your AI assistant's configuration file:

{
  "mcpServers": {
    "tianji": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "tianji-mcp-server"
      ],
      "env": {
        "TIANJI_BASE_URL": "https://tianji.example.com",
        "TIANJI_API_KEY": "<your-api-key>",
        "TIANJI_WORKSPACE_ID": "<your-workspace-id>"
      }
    }
  }
}

Environment Variable Configuration​

Before using Tianji MCP Server, you need to set the following environment variables:

# Tianji platform API base URL
TIANJI_BASE_URL=https://tianji.example.com

# Tianji platform API key
TIANJI_API_KEY=your_api_key_here

# Tianji platform workspace ID
TIANJI_WORKSPACE_ID=your_workspace_id_here

Getting an API Key​

You can obtain a Tianji platform API key by following these steps:

  1. After logging into the Tianji platform, click on your profile picture in the top right corner
  2. Select Profile from the dropdown menu
  3. On the profile page, find the API Keys option
  4. Click on create new key, and follow the prompts to complete the key creation

Usage Instructions​

Tianji MCP Server provides a series of tools that can interact with AI assistants through the MCP protocol. Below are detailed descriptions of each tool:

Query Survey Results​

Use the tianji_get_survey_results tool to query result data for a specific survey.

Parameters:

  • workspaceId: Tianji workspace ID (defaults to the value configured in environment variables)
  • surveyId: Survey ID
  • limit: Limit on the number of records returned (default 20)
  • cursor: Pagination cursor (optional)
  • startAt: Start time, ISO format, example: 2023-10-01T00:00:00Z
  • endAt: End time, ISO format, example: 2023-10-31T23:59:59Z
  • filter: Filter conditions (optional)

Get Survey Information​

Use the tianji_get_survey_info tool to get basic information about a specific survey.

Parameters:

  • workspaceId: Tianji workspace ID (defaults to the value configured in environment variables)
  • surveyId: Survey ID

Get All Survey List​

Use the tianji_get_all_survey_list tool to get a list of all surveys in the workspace.

Parameters:

  • workspaceId: Tianji workspace ID (defaults to the value configured in environment variables)

Get Website List​

Use the tianji_get_website_list tool to get a list of websites in the workspace.

Parameters:

  • workspaceId: Tianji workspace ID (defaults to the value configured in environment variables)

Usage Examples​

Below are examples of natural language interactions between users and AI assistants integrated with Tianji MCP Server:

Example 1: Get All Survey List​

User: Help me view all my survey questionnaire lists

AI Assistant: I'll get all your survey questionnaire lists for you.
[AI Assistant calls tianji_get_all_survey_list through MCP protocol to get data]
Based on the data in your workspace, you currently have the following surveys:
1. User Experience Satisfaction Survey (created on 2023-09-15)
2. Product Feature Feedback Survey (created on 2023-10-01)
3. Website Usability Assessment (created on 2023-10-20)

Example 2: Get Specific Survey Details​

User: Please tell me the details of the "User Experience Satisfaction Survey"

AI Assistant: I'll query the details of that survey for you.
[AI Assistant calls tianji_get_survey_info through MCP protocol to get data]
Details of the "User Experience Satisfaction Survey":
- Creation time: 2023-09-15
- Status: Active
- Number of questions: 10
- Responses collected: 128
- Most recent response: 2023-10-25

Example 3: Query Survey Results​

User: Help me analyze the October results of the "Product Feature Feedback Survey"

AI Assistant: I'll analyze the October results of the "Product Feature Feedback Survey".
[AI Assistant calls tianji_get_survey_results through MCP protocol to get data for the specific time range]
Analysis of the October "Product Feature Feedback Survey" results:
- Total responses: 42
- Most popular feature: Automated Reports (85% positive feedback)
- Feature most in need of improvement: Mobile adaptation (mentioned by 62%)
- Average satisfaction rating: 4.2/5
- Main user suggestions: Add data export functionality, optimize page loading speed