TalentMe Official MCP Guide & Setup

By configuring the Model Context Protocol (MCP), seamlessly connect your IDE's AI Agent (like Cursor / Claude Code / Cline) with the TalentMe cloud knowledge base and your local memory tree.

🐈 GitHub Repo (talentme-mcp)

TalentMe MCP Toolchain Architecture

💻Your AI IDE (Cursor / Cline)

Intent Recognition & Tool Calling

↓

🤖TalentMe MCP ServerIncludes 20+ Built-in System Tools

↙Read / Write

↓Status Sync

↘Diag & Coach

🗂️

Local Wiki

Build structured notes, scan for dead links and maintain wiki health.

☁️

Cloud Mastery Graph

Sync real-time progress, turning your coding history into structured data.

👨‍🏫

Expert Coaching

Manage mock interview states and import expert rubrics for precise guidance.

Method 1: One-Click Installer (Recommended)

We provide an automated installer script that handles environment validation, creates an isolated Python 3.10+ virtualenv, downloads dependencies, and guides you through database and IDE integration.

Execute this command in your macOS / Linux terminal:

curl -fsSL https://talentme.airsota.com/install.sh | bash

The installer script will automatically:

Verify python3 >= 3.10 and git are installed.
Clone and install the client inside a secure sandbox (~/.talentme_venv).
Prompt you to enter your registered email and License Key.
Automatically update Cursor and Claude Desktop config with absolute paths.

Method 2: Manual IDE Configuration (Alternative)

If you are using extensions like Cline that cannot be auto-detected, or if you prefer to manually control your config files, please refer to this guide.

Step 1: Locate Config File

Open VSCode, find the MCP config option in the Cline extension settings, or directly edit the cline_mcp_settings.json file in your workspace root.

Step 2: Enter JSON Configuration

Paste the following configuration into the config file. Remember to replace YOUR_LICENSE_KEY with your TalentMe subscription key.

{
  "mcpServers": {
    "talentme": {
      "command": "talentme",
      "args": [
        "start"
      ],
      "env": {
        "TALENTME_EMAIL": "YOUR_ACCOUNT_EMAIL",
        "TALENTME_LICENSE_KEY": "YOUR_LICENSE_KEY",
        "TALENTME_MEMORY_PATH": "YOUR_LOCAL_MEMORY_PATH"
      }
    }
  }
}

💡 Note: If your IDE shows 'spawn talentme ENOENT' (Command not found), this is because GUI apps do not inherit terminal paths. Please replace 'command' with the absolute path on your system, e.g., '~/.talentme_venv/bin/talentme' on macOS/Linux or 'C:\Users\YOUR_NAME\.talentme_venv\Scripts\talentme.exe' on Windows.

Step 3: Test Connection

Save the configuration and restart your IDE/client. Upon successful connection, you will see a hammer 🛠️ icon above the Agent's prompt input box. Click it to see all available Tools provided by talentme. You can also directly test by asking the Agent: "Use TalentMe MCP to get the latest ML knowledge graph."

Common CLI Commands

Type talentme in your terminal to invoke the CLI. Below are the core commands for daily maintenance:

talentme setup

Interactive initialization. Configure DB paths, bind email/License, and auto-generate IDE config files.

talentme update

One-click upgrade of the local MCP client and all built-in Agent Skills to the latest version.

talentme sync

Pull and sync the latest knowledge base templates and interview question banks from the cloud to your local workspace.

talentme start

Start the MCP Server process (usually called automatically by the IDE, used for testing).

Setup successful? Come see what specific Tools you can use:

View all Tools list & Dev logs →