Using Linkly AI in WorkBuddy

What You Can Do

Reference local documents when creating tasks

When creating tasks in WorkBuddy, let AI first search your relevant local materials through Linkly AI, then combine the retrieved results to complete reports, proposals, and other tasks — outputs that are traceable and grounded in real sources.

Collaborate with Tencent ecosystem connectors

Combine your local knowledge base with built-in connectors like Tencent Docs and Tencent Lexiang. WorkBuddy can simultaneously retrieve cloud collaboration content and local private documents, covering a more complete range of information sources.

Persistent knowledge source for your AI assistant

Using WorkBuddy’s Assistant feature, let AI call Linkly AI at any time during conversations to search your notes, reference materials, and historical documents — no need to manually upload attachments each time.

Prerequisites

WorkBuddy installed
Linkly AI Desktop running with the MCP service active

Configuration Steps

Local MCP HTTP (Recommended)
Remote MCP
CLI Stdio (Fallback)

Open Connectors

Click Experts·Skills·Connectors in the left navigation, switch to the Connectors tab at the top, then click Custom connectors in the top right.

WorkBuddy Connectors entry and Custom connectors button

Open the MCP configuration editor

In the MCP Server Management dialog that appears, click Configure MCP in the top right to open the JSON configuration editor.

Fill in the configuration and save

Enter the following configuration in the editor, then click Save:

{
  "mcpServers": {
    "linkly-ai": {
      "url": "http://127.0.0.1:60606/mcp"
    }
  }
}

Trust the server

After saving, return to the MCP list, find the linkly-ai entry, and click Trust to complete the first-time authorization.

Complete remote access configuration first, with the desktop tunnel showing ● Connected.

Open Connectors

Same as above — go to Connectors → Custom connectors → Configure MCP.

Fill in the remote configuration and save

Enter the following configuration in the editor, then click Save:

{
  "mcpServers": {
    "linkly-ai": {
      "url": "https://mcp.linkly.ai/mcp"
    }
  }
}

After saving, click Trust in the MCP list to authorize.

Install Linkly AI CLI first.

Open Connectors

Same as above — go to Connectors → Custom connectors → Configure MCP.

Fill in the CLI configuration and save

Enter the following configuration in the editor, then click Save:

{
  "mcpServers": {
    "linkly-ai": {
      "command": "linkly",
      "args": ["mcp"]
    }
  }
}

After saving, click Trust in the MCP list to authorize.

Getting Started

Once configured, simply describe your needs when creating a new task in WorkBuddy and AI will automatically call Linkly AI to search and read your local documents.

Examples:

“Search my local materials and compile an analysis report on XX”
“What content about project requirements is in my documents?”

FAQ

linkly-ai shows a yellow dot in the MCP list

Yellow means it is connecting — wait a moment and it usually turns green. If it stays yellow, check that Linkly AI Desktop is running and the MCP service shows Running.

No Trust button visible after saving

Click Back to MCP List to return to the list, then expand the linkly-ai entry to see the Trust button.

Where is the MCP configuration file located

WorkBuddy’s user-level MCP configuration is stored at ~/.workbuddy/mcp.json. The full path is shown in the Configuration File Path field at the top of the Configure MCP editor.

​What You Can Do

​Prerequisites

​Configuration Steps

​Getting Started

​FAQ

What You Can Do

Prerequisites

Configuration Steps

Getting Started

FAQ