How to Use the Chaindesk MCP in Windsurf

Q: Can Windsurf Cascade autonomously update my Chaindesk datastores?

Yes, Cascade uses upsertdatasource to sync your local workspace markdown files directly with your remote datastore. It handles the entire multi-step sync without requiring you to manually run individual commands.

Q: How does Windsurf handle multiple Chaindesk agents?

Cascade calls listagents to map out all your active bots. You can then instruct Cascade to target a specific agent ID for updates or queries based on the task you are working on.

Build, update, and query custom support agents directly inside Windsurf using Cascade's autonomous multi-step execution.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Chaindesk MCP to Windsurf

Create your Vinkius account to connect Chaindesk 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 Chaindesk with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Custom Datastores and Agents

This Chaindesk MCP Server lets Cascade run `create_agent` and `upsert_datasource` to assemble custom knowledge bases without leaving your editor. You feed Windsurf a directory of support docs, and Cascade automatically parses them, creates the target datastore, and spins up a new agent. It skips the manual web UI setup entirely. Because Cascade chains actions, it checks if a datastore exists via `get_datastore` before writing duplicate files. If your local workspace documentation changes, the IDE immediately updates the remote agent so your support bots stay accurate.

Windsurf Cascades Support Conversations

Managing active conversations happens directly in Cascade using the `list_conversations` and `get_messages` tools. When a support ticket fails, you can ask Cascade to pull the exact transcript from your Chaindesk agent and analyze where the conversation went off track. Instead of jumping between tools, Cascade reads the chat history, identifies the missing documentation, and uses your local codebase to draft a fix. It then pushes the updated info back to your live agent in a single, autonomous loop.

Query and Test Agents Live

Testing your customer-facing bots is handled by Cascade using the `query_agent` and `update_agent` tools. You can prompt Cascade to run a test suite of customer questions against your Chaindesk setup to verify its responses. If the agent hallucinates or gives a weak answer, Cascade immediately rewrites the system prompt. It updates the configuration on the Vinkius MCP host instantly, letting you verify the fix in seconds.

Setup guide

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

mcp_config.json

{
  "mcpServers": {
    "chaindesk-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 Chaindesk. 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 Chaindesk 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 Chaindesk MCP in Windsurf

Open your Windsurf settings and add the Vinkius MCP Server URL to your mcp_config.json file. Cascade instantly registers the tools and lets you query or update your custom agents right away.

Yes, Cascade uses `upsert_datasource` to sync your local workspace markdown files directly with your remote datastore. It handles the entire multi-step sync without requiring you to manually run individual commands.

Cascade calls `list_agents` to map out all your active bots. You can then instruct Cascade to target a specific agent ID for updates or queries based on the task you are working on.

No, this MCP Server exposes direct tools for managing no-code agents. You write the prompts in plain English, and Cascade handles the API calls to configure them.

Your data remains private because Vinkius runs this server inside an isolated, ephemeral V8 sandbox. Your uploaded PDF files and support transcripts are transmitted securely via encrypted endpoints directly to Chaindesk, ensuring your raw data never leaks.

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