How to Use the Coze MCP in Windsurf

Q: How does Windsurf run Coze bots autonomously?

Cascade uses createchat to prompt your bot, then automatically handles any required tool calls using submittooloutputs. It chains these steps in the background without needing your permission for every single message.

Q: Can I sync my local codebase docs with Coze using Windsurf?

Yes, Cascade reads your local files and uses uploaddocument to push them straight to your Coze datasets. It keeps your remote bot's knowledge base in sync with your active git branch.

Q: How do I view past chat sessions from the IDE?

The agent calls getconversationhistory to pull recent messages from any active session. You can inspect the logs directly inside your workspace without opening a browser.

Trigger Coze bots and sync RAG datasets directly from your Windsurf Cascade workspace.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Coze MCP to Windsurf

Create your Vinkius account to connect Coze 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 Coze with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Coze Workspaces and Bots in Cascade

The `list_workspaces` tool connects Windsurf directly to your Coze setup. This MCP Server exposes tools so Cascade can grab your workspace IDs, find the right bot drafts, and publish them with `publish_bot` without you clicking around the Coze UI. Instead of jumping between tabs, your IDE handles the lifecycle. Cascade looks at your local code changes, decides when a bot needs an update, and pushes the changes live.

Run Multi-Turn Coze Chats Directly in Windsurf

The `create_chat` tool lets Cascade start conversation sessions with your published bots and handle the back-and-forth. If a bot requires external tool outputs, Cascade uses `submit_tool_outputs` to feed that data back into the run automatically. When a conversation gets cluttered, the agent runs `clear_conversation` to reset the session state. It keeps your context window clean during long debugging runs.

Sync Local Context with Knowledge Base Datasets

The `upload_document` tool feeds local files and raw text directly into your Coze knowledge base datasets. Cascade scans your workspace, detects out-of-date documentation, and uses `upload_file_url` or `delete_document` to keep your RAG sources fresh. By calling `list_datasets`, Cascade maps out your existing knowledge bases. It modifies the files on the fly, ensuring your custom bots always reference the latest code patterns.

Setup guide

Set up Coze 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 Coze 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 Coze payment history." If connected, Cascade will call the Coze tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "coze-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 Coze. 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 Coze 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 Coze MCP in Windsurf

Cascade uses `create_chat` to prompt your bot, then automatically handles any required tool calls using `submit_tool_outputs`. It chains these steps in the background without needing your permission for every single message.

Yes, Cascade reads your local files and uses `upload_document` to push them straight to your Coze datasets. It keeps your remote bot's knowledge base in sync with your active git branch.

Open your Windsurf settings or edit your config file directly. Add the server entry under the mcpServers key, and this MCP connection lets you load the tools.

The agent calls `get_conversation_history` to pull recent messages from any active session. You can inspect the logs directly inside your workspace without opening a browser.

Your Coze API tokens and uploaded document content stay entirely inside the Vinkius sandboxed environment. The MCP gateway uses ephemeral V8 isolates, meaning your sensitive workspace IDs and raw text documents are never stored or exposed to third parties.

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