How to Use the CHATFLY MCP in Claude
Manage your CHATFLY bots and analyze conversations without leaving the Claude Desktop app.
Works with every AI agent you already use
…and any MCP-compatible client
Connect CHATFLY MCP to Claude Desktop
Create your Vinkius account to connect CHATFLY to Claude Desktop and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.
Check on your chatbots from chat
Get a quick status update on all your bots. Use `list_chatfly_bots` to see everything at once, then drill down with `get_chatbot_details` for specifics. You can also see what files a bot has been trained on with `list_uploaded_documents`. This isn't about opening another browser tab. In Claude Desktop, you just ask. The MCP server connects to CHATFLY, and the answers appear right in your chat, letting you check bot configurations or knowledge base files while you're writing a report.
Retrain bots and test responses in Claude
Kick off a new training cycle or test a bot's new knowledge. The `trigger_bot_training` tool tells a bot to re-index its documents. Then, use `send_bot_message` to have a quick conversation and see if the changes worked. It's a fast feedback loop. You can ask Claude to train the bot, wait a moment, and then ask it to send a test message. All the output—the confirmation, the bot's reply—is right there in your conversation history. No context switching.
Review user conversations with your MCP Server
See how people are actually using your bots. The `list_fly_conversations` tool pulls recent chats, and `get_conversation_history` lets you read through an entire exchange. It's a direct line into your user engagement. With this MCP server connected, you can ask Claude to summarize recent support issues or find conversations that mention a specific topic. You get the raw data you need to improve your bots without having to log into the CHATFLY dashboard.
Set up CHATFLY MCP in Claude Web or Desktop
- 1
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
- 2
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcpReplace[YOUR_TOKEN_HERE]with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials. - 3
Start a conversation
Open a new chat. The CHATFLY MCP tools are available immediately — no restart needed.
Endpoint URL
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp No configuration file needed — paste the URL directly in the Claude web interface.
Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.
Why Choose Vinkius
Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.
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 Desktop
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
Start using the CHATFLY MCP today
We host it, we monitor it, we maintain it. You just paste one token.