Skip to main content

MCP

πŸ’‘ Tip: This feature is only supported in V4.1 and above

What is MCP​

MCP (Model Control Plane) is the central module in AI Studio for connecting AI models with external systems.
Its purpose is to help Agents "access more capabilities," enabling intelligent agents not only to answer questions but also to actually perform tasks, access systems, and call data.
Simply put: MCP is the key component that transforms AI from 'being able to talk' to 'being able to act'.

Functional Modules​

Function CategoryMain Purpose
Computing ServiceAddition, subtraction, multiplication, division, modulo, square root, exponentiation
Search ServiceWeb search, academic paper retrieval, data extraction
Data AnalysisChart generation, analytical capabilities
Tool IntegrationMap services, collaboration tool integration

Core Features of MCP​

  1. Unified Connection: Centrally manage models from different sources and external APIs, allowing AI to flexibly utilize multiple intelligent resources.
  2. Permissions & Security: Supports organization-level and individual-level access control to ensure enterprise data security and compliant invocation.
  3. Flexible Expansion: Freely add new models or system interfaces according to business needs, expanding AI capabilities at any time.
  4. Seamless Integration: Closely collaborates with AI Studio's Agent, Skill, and App modules, easily realizing the complete process from model invocation to task execution.

Example Analogy​

You can think of MCP as the "plugin center for AI" or the "control room":

  • When you install a new app on your phone, it gains new functionality;
  • Similarly, when an Agent connects to a new MCP, it gains new capabilities.

For example:

  • By connecting a "Weather Query MCP," the Agent can answer weather-related questions;
  • By connecting a "CRM System MCP," the Agent can query customer information and generate sales reports;
  • By connecting a "Document Analysis MCP," the Agent can help you extract contract content and key data.

Application Scenarios​

MCP has a wide range of applications, with common business scenarios including:

  • Automated Data Processing: Allowing Agents to automatically extract data from systems, generate reports, or complete approvals.
  • Intelligent Q&A and Information Retrieval: Connecting to enterprise knowledge bases or third-party information sources for precise responses.
  • Cross-System Collaboration: Enabling AI to interact with multiple business systems simultaneously to complete complex tasks (such as ticket creation, customer notifications, etc.).
  • Personalized Extension: Individual users can connect their own tools or APIs via MCP to create a personalized AI assistant.

With MCP, your Agent is no longer just a "question-answering assistant,"
but an intelligent work partner that truly understands business, executes tasks, and connects systems.