> ## 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.

# Integration Overview

> There are only four ways to connect Linkly AI to an AI tool. Understand the differences first, then head to the setup page for your client.

Linkly AI hands its retrieval capability to AI assistants through **MCP (Model Context Protocol)**. The setup pages for twenty-plus clients all look different, but underneath there are only **four connection paths**. Figure out which one you need first, then go to the page for your client — it will save you a lot of trial and error.

***

## The four paths

| Path                   | How it connects                                            | Who it's for                                               | Desktop app running?  | Cost |
| ---------------------- | ---------------------------------------------------------- | ---------------------------------------------------------- | --------------------- | ---- |
| **Local MCP (HTTP)**   | `http://127.0.0.1:60606/mcp`, server name `linkly-ai`      | Clients running on this computer — **the vast majority**   | Yes                   | Free |
| **CLI bridge (stdio)** | Command `linkly`, argument `mcp`                           | Clients that only support stdio transport                  | Yes                   | Free |
| **Cloud Library**      | `https://mcp.linkly.ai/mcp`, server name `linkly-ai-cloud` | Content that should live off your machine and stay online  | **No**                | Free |
| **Remote tunnel**      | `https://mcp.linkly.ai/mcp` (requests tunnel back to you)  | Letting cloud AI apps read **everything** on your computer | Yes, tunnel connected | Pro  |

<Tip>**When in doubt, pick the first one.** If your client is installed on your own computer — Claude Code, Cursor, Cherry Studio and the like — local MCP is the easiest route: the MCP server is ready as soon as the desktop app starts, no account required and no internet connection needed.</Tip>

### How to decide quickly

<Steps>
  <Step title="Where does your client run?">
    **On your computer** (Claude Code, Cursor, Cherry Studio, Raycast…) → use **local MCP**; if the client only supports stdio, use the **CLI bridge** instead.

    **On someone else's server** (ChatGPT, Claude.ai and other web apps) → they can't reach your `127.0.0.1`, so only the two cloud paths are available.
  </Step>

  <Step title="How much should the AI be able to read?">
    **Only a specific set of documents** → use a [Cloud Library](/docs/en/use-cloud-library) and push that content up. Available on free accounts, and it works **even when your computer is off**.

    **Every document on your computer** → use the [remote access tunnel](/docs/en/use-in-remote). This is a Pro feature, and it requires the desktop app to stay running with the tunnel connected.
  </Step>
</Steps>

<Note>The last two paths share the same endpoint, `https://mcp.linkly.ai/mcp`. They are told apart by **whether a cloud library is specified at query time**: specify one and the cloud copy is searched; omit it and the request routes back to your own machine by default (that is, through the tunnel). So give them different server names in your client (`linkly-ai-cloud` vs `linkly-ai`) and you can keep both configured side by side without interference.</Note>

***

## Common prerequisites

Whichever path you take, these two steps are worth doing first:

<CardGroup cols={2}>
  <Card title="Install and run the desktop app" icon="desktop" href="/docs/en/quickstart">
    The MCP server starts automatically with the desktop app on port `60606` by default. If that port is taken it moves to the next one; the actual port is shown under **Settings → MCP**.
  </Card>

  <Card title="Install Linkly AI Skills" icon="wand-magic-sparkles" href="/docs/en/use-skills">
    Skills teach your AI assistant **when to search, when to look at an outline, and how to page through a long document**. With the same tools, an assistant that has Skills installed is noticeably better at using them.
  </Card>
</CardGroup>

<Card title="Let AI set it up for you" icon="robot" href="/docs/en/agent-setup">
  Already have an AI assistant that can run commands? Send it this message and it will read the docs and walk you through the whole thing:

  ```
  Please install the Agent Skill linkly-ai-skills and complete the LinklyAI tool integration. Reference: https://linkly.ai/docs/en/use-skills
  ```
</Card>

***

## Find your client's setup page

### AI assistants

<CardGroup cols={3}>
  <Card title="Claude" href="/docs/en/integration/use-in-claude">
    Web app, cloud path
  </Card>

  <Card title="Claude Cowork" href="/docs/en/integration/use-in-cowork">
    Desktop assistant
  </Card>

  <Card title="ChatGPT" href="/docs/en/integration/use-in-chatgpt">
    Web app, cloud path
  </Card>

  <Card title="OpenClaw" href="/docs/en/integration/use-in-openclaw">
    Open-source agent platform
  </Card>

  <Card title="Cherry Studio" href="/docs/en/integration/use-in-cherry-studio">
    Multi-model client
  </Card>

  <Card title="Raycast AI" href="/docs/en/integration/use-in-raycast">
    macOS productivity tool, needs the CLI bridge
  </Card>

  <Card title="QwenPaw" href="/docs/en/integration/use-in-qwenpaw">
    Qwen agent
  </Card>

  <Card title="WorkBuddy" href="/docs/en/integration/use-in-workbuddy">
    AI work assistant
  </Card>

  <Card title="QoderWork" href="/docs/en/integration/use-in-qoderwork">
    Desktop AI work assistant
  </Card>
</CardGroup>

### Coding agents

<CardGroup cols={3}>
  <Card title="Cursor" href="/docs/en/integration/use-in-cursor">
    AI editor
  </Card>

  <Card title="Windsurf" href="/docs/en/integration/use-in-windsurf">
    AI IDE
  </Card>

  <Card title="GitHub Copilot" href="/docs/en/integration/use-in-github-copilot">
    Inside VS Code
  </Card>

  <Card title="Codex" href="/docs/en/integration/use-in-codex">
    OpenAI command-line assistant
  </Card>

  <Card title="Claude Code" href="/docs/en/integration/use-in-claude-code">
    Anthropic command-line assistant
  </Card>

  <Card title="Gemini CLI" href="/docs/en/integration/use-in-gemini-cli">
    Google terminal agent
  </Card>

  <Card title="ZCode" href="/docs/en/integration/use-in-zcode">
    Coding agent built on GLM
  </Card>

  <Card title="Kimi Code" href="/docs/en/integration/use-in-kimi-code">
    Kimi command-line agent
  </Card>
</CardGroup>

### AI workflows and others

<CardGroup cols={3}>
  <Card title="n8n" href="/docs/en/integration/use-in-n8n">
    Workflow automation
  </Card>

  <Card title="Dify" href="/docs/en/integration/use-in-dify">
    AI app development platform
  </Card>

  <Card title="LM Studio" href="/docs/en/integration/use-in-lm-studio">
    Local LLM client
  </Card>
</CardGroup>

***

## Your client isn't listed?

MCP is an open protocol — any client that supports it can connect to Linkly AI. The pages above just spell out the exact clicks for common clients; **the configuration itself is universal**:

<CardGroup cols={2}>
  <Card title="Supports HTTP / StreamableHTTP" icon="globe">
    Set the URL to `http://127.0.0.1:60606/mcp` and the server name to `linkly-ai`. No auth header required.
  </Card>

  <Card title="Only supports stdio" icon="terminal">
    Set the command to `linkly` and the argument to `mcp`. You'll need to [install the CLI](/docs/en/use-cli) first.
  </Card>
</CardGroup>

Once configured, one search is enough to verify it:

<Prompt description="Search my documents for content about XX">Search my documents for content about project management</Prompt>

If you'd like a dedicated setup page for a particular client, let us know in the [community](/docs/en/community).

***

## Further reading

* [Using MCP](/docs/en/use-mcp) — full configuration for local and LAN modes
* [Using the CLI](/docs/en/use-cli) — stdio bridge and command-line search
* [Remote Access](/docs/en/use-in-remote) — the Pro-only public tunnel
* [Using Cloud Libraries](/docs/en/use-cloud-library) — the path that doesn't depend on your computer being on
* [Tool Reference](/docs/en/tools-intro) — every tool your AI assistant gets, and its parameters
* [Using Skills](/docs/en/use-skills) — teaching your AI assistant to use the tools well