How to Use the CHATFLY MCP in Windsurf

Q: How do I connect CHATFLY to Windsurf Cascade?

Open your local /.codeium/windsurf/mcpconfig.json file and add this MCP server to your configuration. Cascade immediately auto-discovers the tools and lets you prompt it to run training cycles or pull chat logs.

Q: Can Windsurf automatically trigger CHATFLY training when I edit docs?

Yes. Cascade chains your file edits to the triggerbottraining tool. It notices when you save documentation files and automatically runs the training sequence.

Q: How does Windsurf display CHATFLY conversation histories?

Cascade uses getconversationhistory to pull raw message logs straight into your active chat panel. You read the exact user queries and bot responses without switching to an external browser tab.

Q: What happens if my support bot exceeds its account limits?

Your Cascade agent calls getchatflyaccountinfo to check your current usage metrics. If you hit a hard ceiling, the tool returns the exact error message so you know when to upgrade your plan.

Get Windsurf to autonomously train your CHATFLY bots and audit live customer conversations without leaving Cascade.

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 Windsurf

Create your Vinkius account to connect CHATFLY to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Train CHATFLY Bots Autonomously in Windsurf

The `trigger_bot_training` tool initiates a new training cycle for your CHATFLY customer support bots directly inside the Windsurf IDE. Cascade reads your local documentation updates, uploads the files, and kicks off the training run without you having to click around a CHATFLY dashboard. By chaining `list_uploaded_documents` with this training trigger, your Cascade agent verifies that the latest technical specs are live in CHATFLY. It handles the entire sync sequence in a single autonomous step when you modify your local markdown files inside Windsurf.

Audit Customer Chats with Cascade and this MCP Server

The `list_fly_conversations` tool fetches the most recent CHATFLY customer interactions directly into your Windsurf Cascade panel. Instead of manually searching through support logs, you tell Cascade to find CHATFLY chats where users struggled, and it pulls the raw logs instantly. Your Cascade agent then runs `get_conversation_history` on those specific sessions to pinpoint where the CHATFLY bot gave a bad answer. Cascade analyzes the transcript, identifies the missing knowledge in Windsurf, and suggests the exact text patch you need to apply.

Inspect Bot Configurations Inside Windsurf

The `get_chatbot_details` tool extracts the exact setup, system prompts, and configuration parameters of any CHATFLY bot directly inside Windsurf. Your agent uses this MCP server to compare your production CHATFLY bots against staging environments to catch prompt drift. It queries `list_chatfly_bots` first to map out your entire CHATFLY support architecture before Cascade drills down into specific bot settings. You see your active limits and usage quotas immediately because the Windsurf agent pulls everything into your active workspace.

Setup guide

Set up CHATFLY MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my CHATFLY payment history." If connected, Cascade will call the CHATFLY tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Open your local `~/.codeium/windsurf/mcp_config.json` file and add this MCP server to your configuration. Cascade immediately auto-discovers the tools and lets you prompt it to run training cycles or pull chat logs.

Yes. Cascade chains your file edits to the `trigger_bot_training` tool. It notices when you save documentation files and automatically runs the training sequence.

Cascade uses `get_conversation_history` to pull raw message logs straight into your active chat panel. You read the exact user queries and bot responses without switching to an external browser tab.

Your Cascade agent calls `get_chatfly_account_info` to check your current usage metrics. If you hit a hard ceiling, the tool returns the exact error message so you know when to upgrade your plan.

Yes, your chat histories and uploaded documents pass through an ephemeral, zero-trust sandbox. Windsurf accesses this data directly via secure API tokens, and your support logs are never stored on intermediate servers.

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