How to Use the Doofinder MCP in Windsurf

Q: How does Windsurf use Doofinder to debug broken search results?

Windsurf uses the searchkeyword tool to run immediate queries against your index. Cascade then compares the returned items with your database to pinpoint indexing mismatches.

Q: Can I test autocomplete behavior in Windsurf with Doofinder?

Yes, you can ask Cascade to run the suggest tool on any partial search term. Windsurf queries your live suggestions and shows you the exact payload returned by your active configuration.

Q: How do I track search analytics using Doofinder inside Windsurf?

You ask Cascade to run getstats to fetch your live search metrics. Windsurf parses the raw stats array so you can spot zero-result queries and trend shifts without leaving your editor.

Q: How does this MCP Server handle large product catalogs?

It relies on searchpagination to handle offsets and limits safely. Cascade uses this tool to step through deep search results without hitting performance bottlenecks.

Get instant storefront search control as Windsurf autonomously chains your Doofinder catalog audits and query testing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Doofinder MCP to Windsurf

Create your Vinkius account to connect Doofinder 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 Doofinder with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run complex Doofinder search tests in Windsurf

`search_keyword` is the primary tool Cascade uses to run instant product lookup tests directly against your search engines. Instead of manually writing queries, you tell Windsurf to test a specific search term. Bottom line: Cascade figures out the steps, executes the keyword search, and verifies your product listings are active. Because Cascade chains multi-step actions, it doesn't stop at the initial lookup. It uses this MCP integration to check for issues and uses `get_items` to inspect the underlying product data to make sure your inventory matches what the user sees.

Autocomplete testing using this MCP Server

`suggest` lets Cascade query your active auto-suggestions to verify what customers see as they type. You give Windsurf a partial search string, and the agent pulls predictive queries to ensure your autocomplete rules are routing traffic to the correct high-priority SKUs. If the suggestions look off, Cascade doesn't wait for your permission to investigate further. It automatically triggers `get_search_engines` to verify your gateway routing and engine configurations are pointing to the correct live index.

Auto-optimize SKU filters and pagination

`search_filtered` isolates specific product attributes by cutting off unrelated SKU branches according to your custom limits. When you ask Windsurf to debug a faulty collection page, Cascade uses this MCP Server to isolate the broken facets and verify why certain items aren't showing up. To handle massive product catalogs, Cascade chains this with `search_pagination` to step through deep search indexes. It tracks your cloud log limits and vault boundaries so you never hit rate limits while debugging large inventory sets.

Setup guide

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

mcp_config.json

{
  "mcpServers": {
    "doofinder-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 Doofinder. 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 Doofinder 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 Doofinder MCP in Windsurf

Windsurf uses the `search_keyword` tool to run immediate queries against your index. Cascade then compares the returned items with your database to pinpoint indexing mismatches.

Yes, you can ask Cascade to run the `suggest` tool on any partial search term. Windsurf queries your live suggestions and shows you the exact payload returned by your active configuration.

You ask Cascade to run `get_stats` to fetch your live search metrics. Windsurf parses the raw stats array so you can spot zero-result queries and trend shifts without leaving your editor.

It relies on `search_pagination` to handle offsets and limits safely. Cascade uses this tool to step through deep search results without hitting performance bottlenecks.

This integration only touches your Doofinder search queries, catalog indices, and search statistics. Windsurf processes these payloads locally within your secure workspace, and credentials never leave your local environment.

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