Skip to main content
Model Context Protocol (MCP) extends Qoder’s capabilities by enabling seamless integration with external systems and data sources. This topic covers the core concepts, supported transport types, configuration steps, and practical use cases for MCP.

​
What is MCP?

MCP is an open protocol that standardizes how applications provide context and tools to large language models (LLMs). By exposing functionality through a consistent interface, MCP allows LLMs to interact with external systems—such as APIs, databases, and local tools—in a structured and secure way.

​
Why use MCP

MCP enables Qoder Agent to connect with a wide range of external systems and data sources via standardized interfaces. This enhances the agent’s ability to:
  • Retrieve real-time information
  • Perform actions in external systems
  • Process structured or unstructured data
It supports personalized workflows and empowers developers to build more intelligent, context-aware AI assistants.

​
How it works

MCP servers expose their capabilities (such as functions and data access) through the MCP protocol. Qoder discovers and invokes these capabilities based on user input and tool metadata. Qoder supports two standard transport types:
  • Standard Input/Output (STDIO)
    • Communication occurs through stdin/stdout streams.
    • Ideal for local tools and command-line integrations.
    • Requires local environment setup—best suited for professional developers.
  • Server-Sent Events (SSE)
    • Uses HTTP POST for client-to-server requests and event streams for server-to-client responses.
    • Hosted remotely—easy to configure and use.
    • Highly recommended for beginners and quick prototyping.

​
Limitations

  • MCP servers are only supported in Agent mode.
  • You can use a maximum of 10 MCP servers simultaneously.

​
Configure MCP servers

1. In the upper-right corner of your Qoder IDE, click the user icon or use the keyboard shortcut (⌘ ⇧ , （macOS）orCtrl shift ,(Windows)), and select Qoder Settings. 2. In the left-side navigation pane, click MCP. 3. Choose to either:
  • Connect to your own MCP server
a. On the My Servers tab, click + Add in the upper-right corner. b. In the JSON file that appears, add your server details:
  • Name
  • Transport type (STDIO or SSE)
  • Command and arguments (for STDIO)
  • Endpoint URL (for SSE) Example: 
    {
 "mcpServers": {
 "github": {
 "command": "npx",
 "args": [
 "-y",
 "@modelcontextprotocol/server-github"
 ],
 "env": {
 "GITHUB_PERSONAL_ACCESS_TOKEN": "<YOUR_TOKEN>"
 }
 }
 }
}
    c. Close the file and click Save when prompted.
After saving, the new server appears in your list. The link icon means the connection is successful. Expand the entry to view the available tools.
  • Use an MCP server in MCP Square
a. Click the MCP Square tab. b. Browse the list of available servers and click Install on the one you want.
Note: Some MCP servers require additional environment variables—such as API_KEY or ACCESS_TOKEN—to function. These must be configured manually.
c.  Go to the My Servers tab to confirm the installation. Expand the details to see the tools list.
Note: If a server fails to start due to missing dependencies, click Quick Fix. If the issue persists, install the dependencies manually. For troubleshooting, see MCP common issues.

​
Use MCP tools

Qoder automatically selects the appropriate MCP tool based on:
  • Your input prompt
  • The tool’s name and description
Before Qoder calls an MCP tool, you are prompted with a confirmation. To automatically run all the subsequent MCP servers, select this confirmation. Then, the agent uses the tool’s output to proceed with the next steps in the workflow.

​
Steps 

  1. In the AI Chat panel, switch to Agent mode and enter your prompt.
  2. Before calling a tool, Qoder prompts for confirmation. Press ⌘ ⏎ (macOS) or Ctrl Enter (Windows) to execute.
  3. After execution, the result appears in the chat. Expand the response to view detailed input and output.
  4. Review any generated code and accept changes as needed.

​
Example scenarios

​
Scenario 1: Retrieve and process web content (remote MCP via SSE)

Use an MCP server to fetch and convert web content from HTML to Markdown for easier reading. Step 1: Get the MCP SSE server endpoint
  1. Visit the official MCP marketplace website.
  2. Copy the SSE endpoint URL for the fetch server.
Step 2: Add the MCP server In the Qoder IDE, go to the MCP page, and edit the MCP server with the following:
  • Name:fetch
  • Type:SSE
  • Server endpoint: Paste the copied URL. 
Example: 
{
  "mcpServers": {
    "fetch": {
      "type": "sse",
      "url": "https://mcp.api-inference.modelscope.net/******/sse"
    }
  }
}
Step 3: Complete configuration Once saved, the link icon confirms the server is ready. Expand the details to see the tools list. Step 4: Use in Qoder In Agent mode, enter:  
Summarize this document: https://docs.qoder.com/user-guide/chat/overview

​
Scenario 2: Query city weather (local MCP via STDIO)

Use a local MCP server to retrieve real-time weather data. Step 1: Check prerequisites Ensure Node.js is installed. You can ask Qoder to verify: 
Check my local environment to ensure Node.js is installed
Step 2: Add an MCP server In the Qoder IDE, go to the MCP page, and edit MCP server with the followings:
  • Name:weather
  • Type:STDIO
  • Command:npx
  • Arguments:
-y @h1deya/mcp-server-weather
Example: 
{
  "mcpServers": {
    "weather": {
      "command": "npx",
      "args": [
        "-y",
        "@h1deya/mcp-server-weather"
      ]
    }
  }
}
Step 3: Complete configuration Once saved, the link icon confirms the server is ready. Expand the details to see the tools list. Step 4: Use in Qoder In Agent mode, enter a prompt such as: 
Check the weather in San Francisco, United States
Then, follow up with: 
Are there any weather alerts in the United States tomorrow?

​
References

⌘I