For the complete documentation index, see llms.txt. This page is also available as Markdown.

External Data Integration

External Data Integration

In real-world scenarios, AI assistants often need to access "real-time data" or "external system data" beyond the knowledge base in order to provide accurate and timely responses. Through MaiAgent's tools (API tools and MCP tools), you can connect data sources from internal enterprise systems or third-party platforms to your AI assistant, building intelligent applications that can query across systems and respond in real time.

Use Cases

  • Public Data Platform Integration: For example, government open data (agriculture, weather, transportation, finance), allowing the AI assistant to obtain the latest public data in real time.

  • Internal Enterprise System Queries: Integrate with internal APIs such as ERP, CRM, HR, and ticketing systems, so the AI assistant can provide personalized information based on employee or customer identity.

  • Third-Party SaaS Integration: Connect to services such as Slack, Notion, Google Drive, and Salesforce to embed the AI assistant into existing workflows.

  • Dynamic Queries and Reports: When data volume is large or changes frequently and is not suitable for the knowledge base, queries can be made in real time through APIs instead.

Integration Workflow

  1. Obtain the Data Source: Identify the API or MCP service to be integrated, and prepare the endpoint, HTTP method, headers, and parameter structure.

  2. Create the Tool: On the MaiAgent platform's Tools page, click New API Tool or New MCP Tool. When creating an API tool, you can paste a cURL command directly and the system will automatically parse the URL, headers, and HTTP method.

  3. Configure the AI Assistant: Add the tool to the AI assistant's list of available tools, and use role instructions to guide the AI assistant on when to call the tool.

  4. Test and Go Live: Test the tool invocation flow through conversation, and review execution status and error messages on the Tool Execution Records page under AgentOps to confirm response accuracy before going live.

Examples

  • Agricultural Data Query: Build a real-time agricultural product transaction query assistant by integrating with the Ministry of Agriculture's public API.

The following sections will demonstrate, through concrete cases, how to complete external data integrations, helping you quickly apply them to your own business scenarios.

Last updated

Was this helpful?