> ## Documentation Index
> Fetch the complete documentation index at: https://linkly.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Using Linkly AI in Windsurf

> Integrate your Linkly AI local knowledge base with Windsurf IDE, letting the AI coding assistant search and read your private documents

## Prerequisites

* [Windsurf](https://windsurf.com) installed
* Linkly AI Desktop running with the MCP service active

## Configuration Steps

<Tabs>
  <Tab title="MCP HTTP (Recommended)" icon="globe">
    Edit the MCP configuration file and add the following to `mcpServers`:

    <CodeGroup>
      ```json macOS / Linux theme={null}
      // ~/.codeium/windsurf/mcp_config.json
      {
        "mcpServers": {
          "linkly-ai": {
            "serverUrl": "http://127.0.0.1:60606/mcp"
          }
        }
      }
      ```

      ```json Windows theme={null}
      // %USERPROFILE%\.codeium\windsurf\mcp_config.json
      {
        "mcpServers": {
          "linkly-ai": {
            "serverUrl": "http://127.0.0.1:60606/mcp"
          }
        }
      }
      ```
    </CodeGroup>

    Save and restart Windsurf.
  </Tab>

  <Tab title="MCP Stdio" icon="terminal">
    First [install Linkly AI CLI](/docs/en/use-cli).

    Edit the configuration file and add the following to `mcpServers`:

    ```json theme={null}
    {
      "mcpServers": {
        "linkly-ai": {
          "command": "linkly",
          "args": ["mcp"]
        }
      }
    }
    ```

    Save and restart Windsurf.
  </Tab>

  <Tab title="Remote Access" icon="globe">
    First complete [remote access configuration](/docs/en/use-in-remote), with the desktop tunnel showing{" "}

    <Badge stroke color="green">
      ● Connected
    </Badge>

    .

    ```json theme={null}
    {
      "mcpServers": {
        "linkly-ai": {
          "serverUrl": "https://mcp.linkly.ai/mcp",
          "headers": {
            "Authorization": "Bearer ${env:LINKLY_API_KEY}"
          }
        }
      }
    }
    ```
  </Tab>
</Tabs>

<Tip>
  The configuration file supports `${env:VAR_NAME}` syntax, allowing you to manage API Keys via environment variables to avoid writing them in plaintext in the configuration file.
</Tip>

## Getting Started

Once configured, ask questions directly in Windsurf's Cascade panel, and Cascade will automatically call Linkly AI's tools. For example:

* "Search my documents for content about API design"
* "Read the project requirements document and summarize the key points"

## FAQ

<AccordionGroup>
  <Accordion title="Tools not showing up in Cascade">
    Confirm that Windsurf has been fully restarted (not just closing the
    window), and that the configuration file JSON format is correct. You can
    check the MCP server status in Cascade settings.
  </Accordion>

  <Accordion title="Tool count limit">
    Windsurf Cascade supports a maximum of 100 tools across all MCP servers. If
    the total number of tools exceeds this limit, some tools may become
    unavailable.
  </Accordion>
</AccordionGroup>