Doofinder MCP. Search, filter, and audit e-commerce data using natural language.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Doofinder. Connect your e-commerce search and analytics directly to your AI agent. Use this server to run advanced keyword searches, apply facet filters (like brand or price), get predictive suggestions, and audit deep catalog indexes from a single conversation.
What your AI agents can do
Get indices
Checks the status of native Gateway authentication indexes.
Get items
Inspects deep internal arrays related to specific product plans.
Get search engines
Runs an automated check on the explicit Gateway history for status validation.
Runs targeted searches using search_keyword to locate specific product records within the platform.
Narrows down large result sets using search_filtered by applying facet parameters like brand, color, or price.
Retrieves fast suggestions for partial queries using the suggest tool, guiding the user to the correct search term.
Orders product listings using search_sorted, allowing the user to specify sorting criteria (e.g., relevance or price).
Retrieves key data points like CTR, click volume, and query velocity using get_stats.
Inspects deep internal arrays and indexes using get_indices or get_items to verify data structure integrity.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Doofinder MCP Server: 10 Tools for E-commerce Search
These tools let your AI agent perform complex, structured e-commerce queries, from basic searches to deep data audits, all through a conversational interface.
019d7588get indices
Checks the status of native Gateway authentication indexes.
019d7588get items
Inspects deep internal arrays related to specific product plans.
019d7588get search engines
Runs an automated check on the explicit Gateway history for status validation.
019d7588get stats
Captures performance metrics like CTR and click rates from native hold parsing.
019d7588search custom
Extracts rich product data by running specialized validations on search queries.
019d7588search filtered
Narrows search results by applying specific property filters (e.g., brand, color, price).
019d7588search keyword
Runs a targeted search for specific product records within the platform.
019d7588search pagination
Retrieves cloud logging data to trace explicit product inventory limits.
019d7588search sorted
Generates a list of products, forcing a specific sort order (e.g., price ascending).
019d7588suggest
Provides predictive search suggestions based on partial queries.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Doofinder, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
You connect your e-commerce search and analytics right into your AI agent. Use this server to run advanced keyword searches, apply facet filters—like brand or price—get predictive suggestions, and audit deep catalog indexes all from one conversation.
Find products by keywords: You run targeted searches using search_keyword to nail down specific product records on the platform. Filter results by attributes: You narrow down huge result sets using search_filtered by applying facet parameters like brand, color, or price. Get predictive search suggestions: You pull fast suggestions for partial queries with suggest, which guides you right to the right search term. Sort results for optimal display: You order product listings using search_sorted, letting you specify sorting criteria like relevance or price. Analyze search performance metrics: You pull key data points like CTR, click volume, and query velocity using get_stats. Audit core catalog data: You check deep internal arrays and indexes using get_indices or get_items to verify data structure integrity.
Beyond that, you can run automated checks on the explicit Gateway history for status validation using get_search_engines, and you can trace explicit product inventory limits by retrieving cloud logging data using search_pagination.
How Doofinder MCP Works
- 1 1. Subscribe to the Doofinder server.
- 2 2. Enter your Doofinder Search Zone, HashID, and Management Token (API Key).
- 3 3. Tell your AI agent what you need (e.g., 'Show me all red running shoes under $100') and let it run the required tools.
The bottom line is, your AI agent handles the complex API calls and data processing using the specialized tools, presenting you with a clear, actionable answer.
Who Is Doofinder MCP For?
E-commerce Managers who need to audit product ranking performance. Digital Marketers who need to verify search analytics and improve conversion rates. Product Owners who monitor category and index mappings across different search engines. Developers who need to test and debug search API parameters.
Monitors search performance, audits product rankings, and verifies conversion metrics without manual testing.
Verifies search analytics and CTR metrics using natural language to plan campaigns and improve conversion funnels.
Monitors category and index mappings across different search engines in real-time to ensure data consistency.
Tests and debugs search API parameters and filtered results by talking directly to the agent.
What Changes When You Connect
- Audit performance metrics immediately.
get_statspulls accurate CTR and query velocity numbers, letting you see exactly where your search funnel is leaking. - Precision filtering saves time. Use
search_filteredto cut through noise, applying filters like 'red' or 'brand X' without manual backend calls. - Never guess a search term again. The
suggesttool gives fast, predictive nodes for partial queries, keeping users on the right track. - Control result order.
search_sortedlets you dictate the payload, forcing custom sorts like 'relevance:desc' or 'price:asc' for specific campaigns. - Go deep into data structure.
get_indicesandget_itemslet you inspect the raw data arrays and catalog limits, which is essential for debugging complex setups. - Test complex queries easily.
search_customhandles complex validations, letting you test niche search logic without writing a single API endpoint.
Real-World Use Cases
Checking seasonal product availability
A product owner needs to know if the 'Summer Collection' is indexed correctly. They ask their agent to run search_keyword for 'summer collection' and then use search_filtered to confirm if the results are limited to the correct brand or category.
Debugging poor search ranking
A developer notices certain products aren't ranking high. They use search_sorted to force a 'relevance:desc' sort and then check get_stats to see if the average CTR is dropping, helping pinpoint the ranking issue.
Validating inventory limits
A supply chain manager needs to verify the full scope of the catalog. They run get_items to inspect deep internal arrays and use search_pagination to ensure all available inventory limits are visible.
Improving site search conversion
A digital marketer wants to boost sales. They ask the agent to run suggest for a partial query, find the best term, then use search_filtered to narrow results by a high-margin attribute (e.g., 'organic').
The Tradeoffs
Using too many basic searches
Trying to find a product by manually running search_keyword first, then running search_filtered with a brand, and then running search_sorted to check prices. This is slow and requires multiple steps.
→
The agent should handle this in one flow. Start with a complex query using search_custom, passing the keyword, filter, and sort parameters together. This reduces calls and gives a single, structured result.
Missing data context
Just running search_keyword for 'shoes' and getting 10,000 results. You have no idea which ones are relevant or if the data is complete.
→
First, run get_indices to validate the authentication context. Then, use search_filtered with specific brand/color parameters to reduce the result set to a manageable, targeted group.
Assuming data is current
Running a search query and assuming the results are the absolute latest inventory. You might miss out-of-sync data.
→
Run search_pagination and get_items together. This confirms the cloud logging trace and inspects deep internal arrays to verify the raw catalog limits are up to date.
When It Fits, When It Doesn't
Use this server if your goal is read-only e-commerce discovery or analytics. You need to know what products exist, how they are structured, or how they rank. Use search_keyword when you know the exact search term. Use search_filtered when you need to cut results by known attributes (like Brand or Price). If you need to predict what a user might search, use suggest. If you need to test complex logic that combines keywords and filters, use search_custom. Don't use this if you are trying to update product data or run transactions—this is read-only data inspection.
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Manually checking product data is a nightmare of tabs and filters.
Right now, checking product data means logging into the dashboard, running a basic search, then manually clicking filters for Brand, then another filter for Color, and finally running a separate report to check the CTR. It's a copy-paste job that takes 20 minutes just to gather the initial numbers.
With the Doofinder MCP Server, you just tell your agent: 'Show me all red running shoes from Brand X, sorted by price, and give me the CTR.' The agent runs `search_filtered` and `search_sorted` in sequence, and you get the full, actionable data set immediately.
Search & Data Retrieval with Doofinder MCP Server
You don't have to manually run `get_indices` to validate auth, then separately run `get_stats` to check performance, and finally combine them. The agent orchestrates this complex sequence of checks for you.
It turns a multi-step, error-prone audit into a single, conversational command. You get the raw data and the performance metrics, all without touching a dashboard.
Common Questions About Doofinder MCP
How do I use `search_filtered` with a specific brand and color? +
You simply tell your agent to filter by those criteria. The tool handles the structural extraction of properties, narrowing the results immediately. It's much faster than using the native UI.
What's the difference between `search_custom` and `search_keyword`? +
search_keyword is for simple, direct searches (e.g., 'running shoes'). search_custom lets you execute richer, validated search logic, combining keywords with other parameters for deeper queries.
Does `get_stats` give me current sales numbers? +
No, get_stats pulls performance analytics like CTR and click limits. It tells you how people are searching, not how many items were sold in the last hour.
How do I get predictive suggestions using the `suggest` tool? +
Just ask the agent to 'Suggest terms for X'. The suggest tool will list multiple options ('iphone 15', 'iphone case', etc.), letting you pick the best term to use next.
How do I check for performance issues using the `get_indices` tool? +
The get_indices tool validates the native Gateway authentication. It shows you the exact structure of the indexes, helping you debug mapping issues or slow data retrieval points.
What information does `search_pagination` provide regarding search results? +
search_pagination retrieves cloud logging data. It tracks explicit vault limits, which is essential for managing large result sets and knowing when to make the next API call.
Can I sort my search results using the `search_sorted` tool? +
Yes, search_sorted provisions a highly-available JSON payload. You specify the desired sort direction, like 'price:asc' or 'relevance:desc', directly in the call.
How do I retrieve product data using the `get_items` tool? +
The get_items tool inspects deep internal arrays. This allows you to pull detailed product information, even for items that might not be immediately visible in standard search results.
Can my agent perform filtered searches using specific product attributes? +
Yes. Use the 'search_filtered' tool. You can specify the 'filter_name' (e.g., 'brand', 'color') and the 'filter_value'. The agent will analyze the global bounds and return results restricted strictly to those custom limits.
How do I monitor the click-through rate (CTR) of my search engine via chat? +
Use the 'get_stats' tool. Your agent will pull raw status configurations and capture exact CTR, total clicks, and query velocity numbers for your search engine, helping you track performance without manual dashboard checks.
Can I check which search engines and indices are active in my account? +
Absolutely. The 'get_search_engines' and 'get_indices' tools allow your agent to dump all isolated tenant indexes mapping explicit hash strings, giving you a full view of your Doofinder infrastructure.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Redo
Manage returns, track shipping protection claims, and oversee exchanges via AI agents with Redo.
Extensiv
Manage omnichannel operations via Extensiv — track orders and shipments, monitor inventory and warehouses, and manage vendors directly from any AI agent.
TaxJar
Calculate, collect, and remit sales tax automatically across every US state and jurisdiction with real-time rate accuracy.
You might also like
Kavita (eBook/Manga)
Manage your Kavita media server—scan libraries, check API status, and authenticate sessions directly from your AI agent.
Hexometer
Automate website monitoring via Hexometer — monitor uptime, performance, and health directly from any AI agent.
Stigg
Automate billing and subscription management via Stigg — provision customers, manage plans, and report usage directly from any AI agent.