> ## 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 Cherry Studio

> Integrate your Linkly AI local knowledge base with Cherry Studio to enhance document retrieval capabilities in multi-model AI conversations

## What You Can Do

> [accordion] Enhance Cherry Studio's knowledge base capabilities
>
> Cherry Studio is a widely-used AI client with a built-in knowledge base, but its simple RAG approach cannot satisfy many users' needs. Linkly AI is a perfect enhancement. Plus, your knowledge base can be used across more AI assistants.

> [accordion] Share one local knowledge base across multiple models
>
> Whether you switch to GPT-4, Claude, or Gemini, access your local documents on your computer through Linkly AI — no need to repeatedly upload the same materials to each model. Configure once and share across all models.

> [accordion] Compare how different models handle private documents
>
> Use the same local documents as input and feed them to different models via Linkly AI, comparing their understanding and analysis quality of the same content to find the model best suited for your use case.

> [accordion] Search local notes anytime during a conversation
>
> Ask "What have I recorded about XX?" directly in a chat. Cherry Studio calls Linkly AI's `search` tool to search all your notes on your computer and responds — without interrupting the conversation flow.

## Prerequisites

* [Cherry Studio](https://cherry-ai.com) installed
* Linkly AI Desktop running with the MCP service active

## Configuration Steps

> [tab] MCP HTTP (Recommended)
>
> **1. Open MCP settings**
>
> In Cherry Studio, go to **Settings → MCP Servers → Add**.
>
> **2. Add Linkly AI MCP**
>
> Fill in the following:
>
> * Name: `linkly-ai`
> * Type: `StreamableHTTP`
> * URL: `http://127.0.0.1:60606/mcp`

> [tab] MCP Stdio
>
> First [install Linkly AI CLI](https://linkly.ai/docs/en/use-cli.md).
>
> **1. Open MCP settings**
>
> In Cherry Studio, go to **Settings → MCP Servers → Add**.
>
> **2. Add Linkly AI MCP**
>
> Fill in the following:
>
> * Name: `linkly-ai`
> * Type: `stdio`
> * Command: `linkly`
> * Args: `mcp`, `--client`, `cherry-studio` (one per line)

## Getting Started

Once configured, ask questions directly in Cherry Studio's AI conversation, and the AI will automatically call Linkly AI's tools to search and read your local documents.

## FAQ

> [accordion] Cannot connect to MCP service
>
> Please check: 1. Whether Linkly AI Desktop is running 2. Whether the MCP service is active 3. Whether the port number is 60606 (you can confirm it under **View MCP connection settings** on the **Agent usage** page of the Linkly AI main window)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.