How to Use the watsonx Discovery MCP in CrewAI

Q: How do I run watsonx Discovery queries with CrewAI?

You assign the querydiscoverycontent tool to a specialized agent. You define that agent's role as 'Data Investigator,' telling it exactly when and how to perform searches across collections.

Q: Can my autonomous crew check data sources with watsonx Discovery and CrewAI?

Absolutely. The agents can call listdiscoverycollections to identify all relevant databases. This is the first step in letting a team know where they should focus their investigation.

Q: Does watsonx Discovery provide enough context for CrewAI's tasks?

Yes. By exposing listavailableenrichments and getdocumentdetails, you give the agents visibility into how data is processed, ensuring their final analysis is based on full context.

Q: What if my research needs to look at specific files with watsonx Discovery and CrewAI?

The listcollectiondocuments tool lets an agent list all document IDs within a collection. This helps the team narrow down which documents are most relevant for analysis.

Run specialized agents collaborating on data analysis with CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect watsonx Discovery MCP to CrewAI

Create your Vinkius account to connect watsonx Discovery 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 watsonx Discovery with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative Data Analysis using MCP Server

Set up an 'Analyst Agent' to use `query_discovery_content`. This agent searches the data collection, and then a separate 'Reporter Agent' takes those results. The Reporter Agent uses the findings to synthesize a final, actionable report. The agents work together in a multi-step process: research first, then analyze.

Defining Research Scope with MCP Server

Give your 'Research Agent' two tools: `list_discovery_collections` and `list_available_enrichments`. The agent uses these to map out all available data sources and understand what type of NLP models are applied. This ensures the whole crew knows its operational boundaries before starting work.

Contextualizing Findings with MCP Server

If an agent finds a key document, it uses `get_document_details` to pull all the necessary metadata. This context is then passed to another agent for review. The 'Moderator Agent' can use this rich data—including details from `list_collection_documents`—to make final decisions or escalate findings.

Setup guide

Set up watsonx Discovery 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 watsonx Discovery tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent watsonx Discovery 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="watsonx Discovery Analyst",
        goal="Access and analyze watsonx Discovery data via MCP.",
        backstory="Expert analyst with direct watsonx Discovery access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent watsonx Discovery 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 watsonx Discovery. 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 watsonx Discovery 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 watsonx Discovery MCP in CrewAI

You assign the `query_discovery_content` tool to a specialized agent. You define that agent's role as 'Data Investigator,' telling it exactly when and how to perform searches across collections.

Absolutely. The agents can call `list_discovery_collections` to identify all relevant databases. This is the first step in letting a team know where they should focus their investigation.

Yes. By exposing `list_available_enrichments` and `get_document_details`, you give the agents visibility into how data is processed, ensuring their final analysis is based on full context.

The `list_collection_documents` tool lets an agent list all document IDs within a collection. This helps the team narrow down which documents are most relevant for analysis.

The server touches indexed content and component settings. The agents access metadata and status details about individual documents to ensure they're only analyzing approved material.

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