Kollektiv Document Management MCP server

Kollektiv MCP provides a personal LLM knowledge base that you can access through your favorite editor or client. It eliminates the need for infrastructure setup, chunking, or syncing - simply upload your data and start chatting. The service works with all major MCP clients including Cursor, Windsurf, Claude Desktop, and more.

Connection Setup

The simplest way to connect to Kollektiv MCP is by adding the following configuration to your editor's mcp.json file:

{
  "mcpServers": {
    "kollektiv": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.thekollektiv.ai/mcp"
      ]
    }
  }
}

Cursor Configuration

1. Open Cursor and go to Cursor Settings > MCP > Add new global MCP Server
2. Paste the configuration above and save (ctrl/cmd+s)
3. If you haven't authenticated before, a browser window will open for login
4. When successful, the Kollektiv MCP indicator will turn green in settings

Windsurf Configuration

1. Open Windsurf and go to Settings -> Windsurf Settings > MCP Servers > View raw config
2. Paste the configuration above and save (ctrl/cmd+s)
3. Restart Windsurf to properly connect
4. When successful, the Kollektiv MCP indicator will turn green in settings

Claude for Desktop Configuration

1. Open Claude Desktop and go to Settings -> Developer > Edit config
2. Open the json file in any text/code editor
3. Paste the configuration above and save (ctrl/cmd+s)
4. Restart Claude Desktop to properly connect
5. When successful, the Kollektiv MCP indicator will turn green in settings

VS Code Configuration

1. Open VS Code and go to Settings -> MCP: Add server > Command (stdio)
2. Set command to npx -y mcp-remote https://mcp.thekollektiv.ai/mcp
3. Set name to kollektiv or any descriptive name
4. Your settings.json should look similar to:

{
  "chat.mcp.discovery.enabled": true,
  "chat.mcp.enabled": true,
  "mcp": {
    "servers": {
      "kollektiv": {
        "type": "stdio",
        "command": "npx",
        "args": [
          "-y",
          "mcp-remote",
          "https://mcp.thekollektiv.ai/mcp"
        ]
      }
    }
  }
}

5. Click Start to connect to the MCP Server
6. Switch to Agent mode to use MCP tools

Cline Configuration

1. Open Cline and click on MCP Servers > Edit Configuration
2. Add the following to your cline_mcp_settings.json:

{
  "mcpServers": {
    "kollektiv": {
      "timeout": 60,
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.thekollektiv.ai/mcp"
      ],
      "transportType": "stdio",
      "disabled": false
    }
  }
}

3. If connection is successful, you'll be guided through authentication

Usage

Available Tools

• /query_documents — Submit a question to your uploaded documents and receive an answer based on those sources
• /list_documents — View a list of your synced documents with basic metadata

Usage Tips

• Always include the phrase "use Kollektiv MCP" so the client knows which tools to call
• After uploading a document, wait 1-2 minutes before querying it
• If the client generates a poor query, edit or rewrite it yourself

Troubleshooting

If you experience connection issues, try these steps:

1. Verify the endpoint: Ensure you're using https://mcp.thekollektiv.ai/mcp

2. Clean mcp-remote cache:

   # MacOS
   rm -rf ~/.mcp-auth  
   
   # Windows
   Remove-Item -Recurse -Force "$env:USERPROFILE\.mcp-auth"
   

3. Clear browser data & cookies (Note: this will sign you out of all active sessions)

4. Restart your MCP client and try reconnecting

MCP Inspector

For debugging, you can use the MCP Inspector:

npx @modelcontextprotocol/inspector

Select either:

• SSE: connect to https://mcp.thekollektiv.ai/sse
• Streamable HTTP: connect to https://mcp.thekollektiv.ai/mcp

For additional support, open a GitHub issue or contact [email protected].

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.