How to Use the MaestroQA MCP in Windsurf

Q: How does Windsurf use MaestroQA to audit support agents?

Cascade calls listqaagents to get your roster and then runs listqatickets to find their graded interactions. It cross-references these lists autonomously, giving you a quick breakdown of who needs coaching without making you click around the browser.

Q: Can I update evaluation rubrics inside Windsurf using MaestroQA?

You can retrieve the current criteria using listqarubrics to see how tickets are graded, but edits must be done in the main platform. This server focus is on pulling those rubrics so Cascade can evaluate local agent code against your actual QA guidelines.

Q: How does the async export process work in Windsurf when using MaestroQA over MCP?

Cascade triggers the export via requestqadataexport and polls getexportdownloadlinks until the files are ready. Because it runs autonomously, you just ask for the data once and Cascade drops the downloaded files directly into your workspace.

Get Cascade to audit support quality and sync CSAT scores directly inside Windsurf without writing custom MCP integrations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MaestroQA MCP to Windsurf

Create your Vinkius account to connect MaestroQA 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 MaestroQA with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate QA reviews with Windsurf Cascade

`list_qa_tickets` acts as the entry point for your autonomous agent to pull support tickets and flag anomalies. Cascade scans the ticket queue, targets low-scoring interactions, and immediately calls `get_ticket_qa_details` to isolate why an agent missed the mark — and this actually matters — because manual auditing is too slow. Instead of you clicking through tabs, this MCP Server lets your agent run the entire investigative loop in one shot. Bottom line is this: it matches bad tickets against active evaluation criteria so you get a finished summary of performance gaps right in your sidebar.

Push CSAT scores directly from your workspace

`push_csat_scores` is the tool Cascade uses to update customer satisfaction metrics in MaestroQA without leaving your editor. The agent reads incoming feedback from your local files, parses the raw numbers, and writes it directly to your QA dashboard. Let's skip the fluff. You don't need to build a custom sync pipeline or run manual CSV imports ever again — that's it.

Export raw QA datasets using autonomous chains

`request_qa_data_export` triggers the backend export process for any date range your agent extracts from your current project context. Cascade initiates the request, waits for the generation to finish, and automatically invokes `get_export_download_links` to pull down the CSV payloads. Honestly, this eliminates the tedious process of manual export polling. Your agent handles the asynchronous waiting cycle in the background while you focus on writing code.

Setup guide

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

mcp_config.json

{
  "mcpServers": {
    "maestroqa-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 MaestroQA. 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 MaestroQA 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 MaestroQA MCP in Windsurf

Cascade calls `list_qa_agents` to get your roster and then runs `list_qa_tickets` to find their graded interactions. It cross-references these lists autonomously, giving you a quick breakdown of who needs coaching without making you click around the browser.

You can retrieve the current criteria using `list_qa_rubrics` to see how tickets are graded, but edits must be done in the main platform. This server focus is on pulling those rubrics so Cascade can evaluate local agent code against your actual QA guidelines.

Cascade triggers the export via `request_qa_data_export` and polls `get_export_download_links` until the files are ready. Because it runs autonomously, you just ask for the data once and Cascade drops the downloaded files directly into your workspace.

No, Vinkius handles the underlying credentials so your editor only needs a single secure endpoint token. You add the server to your configuration and Cascade instantly discovers all seven tools on the MCP Server.

Your raw ticket details, CSAT scores, and agent lists are processed inside an ephemeral V8 sandbox that destroys itself after execution. No support data is cached or stored on Vinkius servers, ensuring complete isolation for sensitive customer transcripts.

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