> ## 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 Cursor

> Integrate your Linkly AI local knowledge base with Cursor, letting the AI coding assistant search and read your project documents

## What You Can Do

<AccordionGroup>
  <Accordion title="Automatically reference requirements documents while coding">
    No more manually copy-pasting requirements. Cursor uses Linkly AI's `read`
    tool to directly read your product specification documents on your computer,
    understanding requirements before generating code — reducing rework caused
    by misunderstandings.
  </Accordion>

  <Accordion title="Precisely search internal project documents">
    Use Linkly AI's `search` tool to quickly locate interface specifications,
    data dictionaries, or technical standards in your local documents — without
    leaving the editor or switching windows.
  </Accordion>

  <Accordion title="Debug with business context">
    When debugging, let Cursor read business logic documents through Linkly AI.
    With an understanding of business rules, the AI can more easily identify the
    root cause — rather than just analyzing code in isolation.
  </Accordion>
</AccordionGroup>

## Prerequisites

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

## Configuration Steps

<Tabs>
  <Tab title="MCP HTTP (Recommended)" icon="globe">
    <Steps>
      <Step title="Open MCP settings">
        In Cursor, go to **Settings → MCP Servers → Add Server**.
      </Step>

      <Step title="Add Linkly AI MCP">
        Fill in the following:

        * Name: `linkly-ai`
        * Type: `StreamableHTTP`
        * URL: `http://127.0.0.1:60606/mcp`
      </Step>
    </Steps>
  </Tab>

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

    <Steps>
      <Step title="Open MCP settings">
        In Cursor, go to **Settings → MCP Servers → Add Server**.
      </Step>

      <Step title="Add Linkly AI MCP">
        Fill in the following:

        * Name: `linkly-ai`
        * Type: `stdio`
        * Command: `linkly`
        * Args: `mcp`
      </Step>
    </Steps>
  </Tab>

  <Tab title="CLI" icon="square-terminal">
    First [install Linkly AI CLI](/docs/en/use-cli). Once installed, Cursor's AI assistant can directly call CLI commands to search and read your documents:

    ```bash theme={null}
    linkly search "keyword"
    linkly read <document-id>
    ```
  </Tab>
</Tabs>

<Tip>
  We recommend also installing [Linkly AI Skills](/docs/en/use-skills) to teach the
  AI assistant how to efficiently use Linkly AI's tools, improving search and
  reading efficiency.
</Tip>

## Getting Started

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

* "Search my documents for content about database design"
* "Read the project's API documentation"

## FAQ

<AccordionGroup>
  <Accordion title="Cannot connect to MCP service">
    Please check: 1. Whether Linkly AI Desktop is running 2. Whether the MCP
    service is active (shown as Running in settings) 3. Whether the port number
    is 60606 (you can confirm in Linkly AI settings)
  </Accordion>
</AccordionGroup>