How to Use the Doofinder MCP in CrewAI

Q: How do CrewAI agents coordinate when searching Doofinder?

One agent uses searchkeyword to find items while another uses getstats to verify search volume. They share this data in memory to make joint decisions on catalog updates.

Q: How does a CrewAI team handle paginated Doofinder search results?

The researcher agent calls searchpagination to step through search results page by page. The agent processes each chunk sequentially, building a complete picture of your catalog's search coverage.

Deploy specialized multi-agent teams to manage and optimize your Doofinder search engines via CrewAI and MCP.

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 CrewAI

Create your Vinkius account to connect Doofinder to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync and verify Doofinder catalogs with CrewAI agents

The `get_indices` tool identifies the precise active product arrays currently loaded into your Doofinder storefront. Your CrewAI catalog manager agent runs this tool to map out the active index structure before handing the data over to the analyst agent. The CrewAI analyst agent then uses `get_items` to verify that high-priority SKUs are correctly indexed in Doofinder. This multi-agent collaboration ensures your Doofinder storefront matches your actual inventory without manual inspection.

Optimize search terms using this MCP Server

The `search_keyword` tool executes test search queries to verify that your top-selling products appear in the Doofinder results. A CrewAI quality assurance agent runs this tool repeatedly during catalog updates to catch any search relevance regressions. If a product is missing from the results, the CrewAI agent calls `get_stats` to check if customers are searching for alternative terms. The crew then automatically logs suggestions to update your search synonyms.

Run deep Doofinder query testing across agent crews

The `search_custom` tool executes complex queries to test how your storefront handles edge-case search terms using this MCP tool. Your testing crew uses this tool to simulate real customer behavior and verify search behavior under different filter combinations. The CrewAI agents analyze the JSON payload returned by this tool, identifying which product attributes are causing search failures. This lets you patch catalog metadata before customers notice the issues.

Setup guide

Set up Doofinder MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Doofinder tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Doofinder Analyst",
    goal="Access and analyze Doofinder data via MCP.",
    backstory="Expert analyst with direct Doofinder access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Doofinder transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Doofinder Analyst",
        goal="Access and analyze Doofinder data via MCP.",
        backstory="Expert analyst with direct Doofinder access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Doofinder transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

One agent uses `search_keyword` to find items while another uses `get_stats` to verify search volume. They share this data in memory to make joint decisions on catalog updates.

Yes, you configure the MCP server with a custom tool filter to only expose read-only tools like `get_stats` or `search_filtered` to specific agents.

The researcher agent calls `search_pagination` to step through search results page by page. The agent processes each chunk sequentially, building a complete picture of your catalog's search coverage.

No, you pass the hosted server URL directly into your agent's `mcps` array parameter during initialization.

The server processes all queries within zero-trust ephemeral sandboxes, ensuring no customer search history is written to disk. All data transmission uses secure HTTPS connections directly to your endpoints.

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