Tools

Tools allow Continue to take action in your IDE and beyond (when you give permission). Currently, they are only supported for the following providers:

• Anthropic - see recommended models here.
• Ollama - see recommended models here.

To use tools, click on the icon in the input toolbar like below.

To let you balance speed and safety, each tool can be set to 1 of 3 modes:

• Automatic: When the LLM requests to use the tool, Continue will automatically call it and send the response to the LLM.
• Allowed: When the LLM requests to use the tool, Continue will first give you the opportunity to "Cancel" or "Continue" with the tool.
• Disabled: The LLM will not know about or be able to use the tool.

Custom tools

Currently custom tools can be configured using the Model Context Protocol, a standard proposed by Anthropic to unify prompts, context, and tool use. Read their quickstart to learn how to set up a local server and then configure your config like this:

YAML

Package or config.yaml

mcpServers:
  - name: My MCP Server
    command: uvx
    args:
      - mcp-server-sqlite
      - --db-path
      - /Users/NAME/test.db

JSON

config.json

{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "transport": {
          "type": "stdio",
          "command": "uvx",
          "args": ["mcp-server-sqlite", "--db-path", "/Users/NAME/test.db"]
        }  
      }
    ]
  }
}