How to Use the Coze MCP in Claude Code

Q: Can I run Coze bot tests from my CI/CD pipeline using Claude Code?

Yes, you can script Claude Code to trigger chats using createchat and verify responses directly in your terminal. This lets you run integration tests on your bots before publishing them.

Q: How does Claude Code update Coze knowledge bases?

The CLI agent uses uploaddocument to push local text files or piped shell outputs straight to your Coze datasets. It uses deletedocument to remove stale files during cleanups.

Q: Can I clear conversation logs from the command line?

Yes, calling clearconversation wipes the message history for the specified session ID. This helps reset your testing environment between automated script runs.

Manage Coze conversations, datasets, and bot deployments directly from your Claude Code terminal.

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 Claude Code

Create your Vinkius account to connect Coze 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 Coze with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pipe Terminal Output to Coze Knowledge Bases

The `upload_document` tool lets Claude Code push local text files, build artifacts, or deployment logs straight to your Coze datasets from the shell. This MCP Server lets you pipe terminal output directly into `upload_file_url` to keep your remote bots updated during CI/CD runs. By combining `list_datasets` and `delete_document`, your terminal agent prunes old training data. This keeps your search indexes clean without needing a web browser.

Run Headless Coze Chats from Claude Code

The `create_chat` tool runs automated conversation sessions with your remote bots directly from your terminal session. Claude Code kicks off the run, monitors the execution, and uses `submit_tool_outputs` to feed system metrics or server states back into the bot. If you need to audit a run, the agent uses `get_conversation_history` to dump the raw JSON logs right to stdout. It makes testing bot logic in bash scripts straightforward.

Automate Bot Deployments with Shell Scripts

The `publish_bot` tool automates your bot release pipeline directly from a terminal command. Claude Code queries your environments using `list_workspaces` and `list_bots`, then pushes the draft bot to production. This turns your bot deployments into a repeatable CLI task. You can trigger updates from cron jobs or post-commit hooks to keep your production agents synced with your codebase.

Setup guide

Set up Coze 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 coze-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http coze-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 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

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": {
    "coze-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 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 Claude Code

Yes, you can script Claude Code to trigger chats using `create_chat` and verify responses directly in your terminal. This lets you run integration tests on your bots before publishing them.

Run the add command with the transport flag in your terminal. This MCP configuration runs over standard transports and is instantly saved to your local config.

The CLI agent uses `upload_document` to push local text files or piped shell outputs straight to your Coze datasets. It uses `delete_document` to remove stale files during cleanups.

Yes, calling `clear_conversation` wipes the message history for the specified session ID. This helps reset your testing environment between automated script runs.

Your Coze API credentials and workspace details are never saved on disk by the server. The MCP environment executes in a sandbox using short-lived V8 containers, keeping your conversation histories and bot configurations private.

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