How to Use the ChatFly MCP in Claude Code

Q: How do I configure Claude Code to use ChatFly?

Run claude mcp add --transport http chatfly -- . Make sure to put all your transport and scope flags before the server name.

Manage ChatFly support bots from your terminal. Connect Claude Code and automate your customer service pipeline.

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 Claude Code

Create your Vinkius account to connect ChatFly to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Provision bots from the command line

Stop clicking through web interfaces to set up support channels. This MCP connection lets you spin up new instances directly from your terminal. You just tell Claude Code to configure a new agent, and it executes `create_bot` instantly. Need to script this across multiple environments? You can pipe your staging config into the CLI. The agent reads your JSON, sets the welcome messages, and outputs the new bot IDs for your deployment scripts.

Automate ChatFly docs in CI/CD via MCP Server

Your support bot should know about new features the second they ship. Hook this MCP Server into your GitHub Actions. When a PR merges, Claude Code grabs the changed markdown files and runs `upload_data_source`. It verifies the current files using `list_data_sources` before pushing. You never have to worry about stale answers again. The bot learns about the release exactly when your users do.

Debug conversations in your shell

Testing chat logic usually requires a clunky UI. Now you can run `chat` straight from your terminal prompt. Send a test query to the bot and watch the raw response stream back into stdout. If the routing logic fails, you can fix it immediately. Just tell your CLI agent to run `update_bot` with a tweaked system prompt. You stay in the terminal, and the issue gets resolved in seconds.

Setup guide

Set up ChatFly MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see chatfly-alternative-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest ChatFly transactions." It will automatically discover and invoke the available ChatFly tools.

Terminal

claude mcp add --transport http chatfly-alternative-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the ChatFly MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "chatfly-alternative-mcp": {
      "type": "url",
      "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 Claude Code

Run `claude mcp add --transport http chatfly -- `. Make sure to put all your transport and scope flags before the server name.

Yes. You can run the CLI headless inside your CI pipeline. It will automatically update your bot's knowledge base whenever you merge new documentation.

The agent uses specific tools exposed by the MCP Server. It can list existing instances, fetch specific details, or modify welcome messages on the fly.

Just ask the CLI to send a message to the bot. It will trigger the chat endpoint and print the response directly to your terminal window.

Vinkius hosts the ChatFly MCP Server in a zero-trust V8 Isolate Sandbox. When you push release notes or customer transcripts through the CLI, the session is ephemeral and tightly scoped.

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