How to Use the CHATFLY MCP in VS Code Copilot

Q: How do I share the CHATFLY tools with my team in VS Code Copilot?

Create a .vscode/mcp.json file in your project's root directory and add the CHATFLY server configuration. Commit this file to your Git repository. Anyone who pulls the repo will automatically have the tools configured in their VS Code Copilot.

Give your entire engineering team access to CHATFLY bot management inside VS Code Copilot.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CHATFLY MCP to VS Code Copilot

Create your Vinkius account to connect CHATFLY to VS Code Copilot and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup CHATFLY with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Standardize bot info for your whole team

Everyone on your team gets the same, up-to-date information about your company's chatbots. Use `list_chatfly_bots` to get a full directory and `get_chatbot_details` to inspect a specific one. The `list_uploaded_documents` tool shows exactly what knowledge a bot is using. By committing the `.vscode/mcp.json` file to your repo, every developer automatically gets these tools in VS Code. When a new engineer clones the project, Copilot is already configured to talk to CHATFLY. No individual setup, no stale info.

Debug bot issues with live conversation data

When a user reports a problem, you can pull the data right into your editor. `list_fly_conversations` finds the user's session, and `get_conversation_history` lays out the entire transcript. It's the fastest way to see what actually happened. In VS Code, your team can collaborate on a fix. One developer can use Copilot to pull the CHATFLY conversation, and another can see the same data and start writing a patch. The shared MCP configuration means everyone is working from the same ground truth.

Use Copilot Agent to manage CHATFLY bots

This isn't just for reading data. Your team can use Copilot to interact with your bots by running `send_bot_message` or trigger a knowledge base update with `trigger_bot_training`. You can also monitor your team's usage with `get_chatfly_account_info`. This creates a consistent workflow. Instead of each developer having their own scripts or methods, the whole team uses the same set of MCP tools in VS Code. It makes managing your CHATFLY bots a repeatable, shared process.

Setup guide

Set up CHATFLY MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the CHATFLY MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the CHATFLY tools listed. Try asking: "List my recent CHATFLY transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "chatfly-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by CHATFLY. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect CHATFLY now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about CHATFLY MCP in VS Code Copilot

Create a `.vscode/mcp.json` file in your project's root directory and add the CHATFLY server configuration. Commit this file to your Git repository. Anyone who pulls the repo will automatically have the tools configured in their VS Code Copilot.

The VS Code integration is for interactive use within the editor. For CI/CD, you'd use a CLI-based client that can connect to the same Vinkius MCP server endpoint. The tools and authentication are the same.

No. The MCP server is configured once with a single Vinkius endpoint token that handles authentication to the CHATFLY API. Your team just needs the `.vscode/mcp.json` file in the project.

Yes. The tools interact directly with the CHATFLY API. If you use `trigger_bot_training`, it changes the live bot, and the next time a teammate uses `get_chatbot_details`, they'll see the updated state.

Vinkius provides a single, secure gateway to the CHATFLY API. All requests from your team's editors are routed through an ephemeral, sandboxed environment. Only the data required for the tool call—like chatbot IDs or conversation transcripts—is processed, and it's never stored by Vinkius.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript