Jentic MCP + Visual Studio Code¶

Goal — In a few minutes, you’ll enable Jentic MCP tools in Visual Studio Code, allowing you to find, inspect, and run external APIs directly in your coding workflow.

What you’ll get¶

With Jentic MCP configured in Visual Studio Code, you'll gain access to powerful tools:

Before you start¶

Ensure you have the following installed and configured:

1. Create an Agent & get your Agent API Key¶

1. Go to https://jentic.com/register and create an account (free).
2. In Credentials, add any API secrets you’ll use (e.g., Discord bot token, NYT key).

3. Open Agents → New Agent, select which APIs/workflows this agent can access, then Generate API Key.

4. Keys are scoped to the APIs you selected and shown once.

5. Set it as an environment variable so VS Code/Copilot can use it:

macOS / Linux

export JENTIC_AGENT_API_KEY="<your-agent-api-key>"

Windows (PowerShell)

setx JENTIC_AGENT_API_KEY "<your-agent-api-key>"
$env:JENTIC_AGENT_API_KEY = "<your-agent-api-key>"  # current session

✅ No more jentic register or JENTIC_UUID. Use JENTIC_AGENT_API_KEY from the Agents page.

2. Configure MCP in Visual Studio Code (Global recommended)¶

The easiest way is to set this up globally so Jentic works in all your projects:

1. Open the Command Palette (macOS ⌘⇧P / Windows/Linux Ctrl+Shift+P, or F1).
2. Run MCP: Open User Configuration — this opens/creates your global mcp.json.

1. Paste the JSON and replace <your-api-key>, then Save:

{
  "servers": {
    "jentic": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/jentic/jentic-sdks.git@main#subdirectory=mcp",
        "mcp"
      ],
      "env": {
        "JENTIC_AGENT_API_KEY": "<your-agent-api-key>"
      }
    }
  }
}

Can't find "MCP: Open User Configuration"? Try updating VS Code (macOS: gear icon → Check for Updates) or see the FAQ below.

(Optional) Per‑project setup¶

If you want to share config with a repo/team or keep it project‑scoped, create .vscode/mcp.json in your workspace instead. You can also run MCP: Add Server and choose Workspace to have VS Code create/populate the file for you.

Note: Cursor and VS Code have separate user profiles, but workspace config (.vscode/mcp.json) works across both editors.

3. Stop repeated permission prompts¶

When Copilot wants to run a Jentic tool, VS Code asks for permission. Click Continue ▾ and choose Always allow – never ask again (all sessions/workspaces).

4. (Optional) Add API keys and environment variables¶

Steps for additional API keys¶

Some APIs returned by /search_apis → /load_execution_info will list required tokens or base‑URLs. Add them once and VS Code passes them automatically.

1. Open the same mcp.json file.
2. Insert or update the env block inside the jentic server.
3. Save the file (you may need to restart VS Code).

Full example after adding keys¶

{
  "servers": {
    "jentic": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/jentic/jentic-sdks.git@main#subdirectory=mcp",
        "mcp"
      ],
      "env": {
        "JENTIC_AGENT_API_KEY": "<your-agent-api-key>",
        "DISCORD_BOTTOKEN": "<your-discord-bot-token>",
        "OPENAI_API_KEY": "<your-openai-api-key>"
      }
    }
  }
}

Security tip: The mcp.json file is plain text. Ensure it's stored securely, especially if it contains sensitive API keys.

5. Use MCP tools in Agent Mode¶

1. Open the Chat view (Windows/Linux: Ctrl+Alt+I; macOS: Control–Command–I). Switch to Agent mode.
2. When prompted to trust the Jentic server, choose Always allow (or Current workspace) to avoid future prompts.
3. Click the Tools icon to see available tools, or reference a tool in your prompt with #tool.

4. Enter a prompt. Copilot will automatically invoke tools as needed, asking for your confirmation before running them.

   You can also directly reference a tool in your prompt by typing # followed by the tool name (e.g., #search_apis).

6. If something doesn’t work¶

Making Visual Studio Code See uvx¶

VS Code is a GUI app; it doesn’t read your shell profile, so binaries added to PATH in .zshrc/.bashrc may be invisible. Choose one of these options:

Option A – Homebrew / System package (macOS & Linux)¶

• Homebrew (macOS) or your distro’s package manager / a sudo pip install uv drops uvx somewhere VS Code already looks:
  • /usr/local/bin on Intel Macs & most Linux distros
  • /opt/homebrew/bin on Apple Silicon

If which uvx returns one of these paths, you’re good – skip this section.

Option B – pip / pipx / pyenv (user-local installs)¶

If uvx lives in a user-local directory, expose it via a symlink (macOS/Linux) or by adding the folder to PATH (Windows).

• macOS / Linux – symlink

  sudo ln -sf "$(which uvx)" /usr/local/bin/uvx   # use /opt/homebrew/bin on Apple Silicon
  sudo ln -sf "$(which uv)"  /usr/local/bin/uv
  

• Windows – PATH
  1. Locate the folder containing uvx.exe (e.g. %USERPROFILE%\AppData\Roaming\Python\Python311\Scripts).
  2. Add that folder to Path in Environment Variables….
  3. Restart VS Code (and any open terminals).

Option C – Hard-code the full path¶

Alternatively, you can skip creating symlinks and directly specify the full path to the binary in the configuration file.

For more details on managing MCP servers in VS Code, see the Official Visual Studio Code MCP server docs.

Additional FAQ¶

Q: Do Cursor and VS Code share MCP configurations?
Cursor and VS Code have separate user profiles, so global configurations don't sync between them. However, workspace config (.vscode/mcp.json) works across both editors.

Q: Should I use global or workspace configuration?
- Global (recommended): Use when you want Jentic available in all projects - Workspace: Use when sharing config with a team or keeping it project-specific

Contact Us Next