As AI systems get better, they’re still held back by their training data and can’t access real-time information or specialized tools. The Model Context Protocol (MCP) fixes this by letting AI models connect with outside data sources, tools, and environments. This allows smooth sharing of information and abilities between AI systems and the wider digital world. This standard, created by Anthropic to bring together prompts, context, and tool use, is key for building truly useful AI experiences that can be set up with custom tools.

​
Quick Start: How to Set Up Your First MCP Server

Simply add the following configuration file to make the Linear MCP server available to your agents:
  • For workspace-specific access: Add to the root of your workspace
  • For global access: Add to your ~/.continue directory
.continue/mcpServers/linear.yaml
name: Linear
version: 0.0.1
schema: v1

mcpServers:
  - name: Linear MCP
    namespace: app.linear/linear ## This uses the slug from the official MCP registry: https://registry.modelcontextprotocol.io
To verify the server is working, run the following prompt: 
Find all open issues assigned to me in Linear and list their titles.

​
Adding an MCP server from the Hub

You can also add an MCP server directly from the Continue Hub. Continue pulls directly from the official MCP registry at registry.modelcontextprotocol.io to provide a one-click install experience for popular MCP servers.

​
Using .mcp.json from Claude, Cursor, Cline, etc

If you have an existing .mcp.json file from Claude, Cursor, Cline, or any other agent that supports the spec, just copy it into your .continue/mcpServers directory and Continue will automatically pick it up.

​
Configuring secrets

For MCP servers that require secret values, such as API keys, you use secrets stored in Continue Hub, or directly set the value:
".continue/mcpServers/supabase.yaml
mcpServers:
  - name: Supabase MCP
    namespace: com.supabase/mcp
    env:
      SUPABASE_ACCESS_TOKEN: ${{ secrets.SUPABASE_ACCESS_TOKEN }} ## Read from Continue Hub secrets

  - name: Supabase MCP
    namespace: com.supabase/mcp
    env:
      SUPABASE_ACCESS_TOKEN: <SUPABASE_ACCESS_TOKEN>

​
Advanced

​
Pointing to a different MCP registry

You can use the registryUrl property to point to a different MCP registry:
.continue/mcpServers/linear.yaml
mcpServers:
  - name: Linear MCP
    namespace: app.linear/linear
    registryUrl: https://my-custom-registry.com

​
How to Configure MCP Servers

To set up your own MCP server, read the MCP quickstart and then create an mcpServers block or add a local MCP server block to your config file:
config.yaml
mcpServers:
  - name: SQLite MCP
    command: npx
    args:
      - "-y"
      - "mcp-sqlite"
      - "/path/to/your/database.db"

​
How to Configure MCP Server Properties

MCP blocks follow the established syntax for blocks, with a few additional properties specific to MCP servers.
  • name: A display name for the MCP server.
  • type: The type of the MCP server: sse, stdio, streamable-http
  • command: The command to run to start the MCP server.
  • args: Arguments to pass to the command.
  • env: Secrets to be injected into the command as environment variables.
For MCP blocks that pull from a registry, use the following properties:
  • namespace: The namespace of the MCP server, e.g. app.linear/linear.
  • registryUrl: (Optional) The URL of the MCP registry to pull from. Defaults to https://registry.modelcontextprotocol.io.

​
How to Choose MCP Transport Types

MCP now supports remote server connections through HTTP-based transports, expanding beyond the traditional local stdio transport method. This enables integration with cloud-hosted MCP servers and distributed architectures.

​
How to Use Server-Sent Events Transport (sse)

For real-time streaming communication, use the SSE transport: 
mcpServers:
  - name: Name
    type: sse
    url: https://....

​
How to Use Standard Input/Output (stdio)

For local MCP servers that communicate via standard input and output: 
mcpServers:
  - name: Name
    type: stdio
    command: npx
    args:
      - "@modelcontextprotocol/server-sqlite"
      - "/path/to/your/database.db"

​
How to Use Streamable HTTP Transport

For standard HTTP-based communication with streaming capabilities: 
mcpServers:
  - name: Name
    type: streamable-http
    url: https://....
These remote transport options allow you to connect to MCP servers hosted on remote infrastructure, enabling more flexible deployment architectures and shared server resources across multiple clients. For detailed information about transport mechanisms and their use cases, refer to the official MCP documentation on transports.