How to Use the IBM watsonx MCP in CrewAI

Q: How do I add the IBM watsonx MCP Server to a CrewAI agent?

Pass the Vinkius HTTP URL directly into the agent's mcps list. CrewAI automatically discovers tools like generatetext and makes them available to that agent in your Vinkius MCP setup.

Run multi-agent teams using CrewAI to coordinate IBM watsonx MCP Server tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect IBM watsonx MCP to CrewAI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploying an IBM watsonx MCP Server in CrewAI

The `generate_text` tool allows individual CrewAI agents to write reports, summarize articles, and analyze data. You assign a specific research task to an agent, and it uses this tool to query your chosen model. Because CrewAI supports role-based specialization, you can have a writer agent take the raw output and refine it. The second agent uses the same MCP server connection to polish the draft without losing context.

Shared Memory Prompt Retrieval

The `list_prompts` tool fetches saved prompt templates from your central project workspace. Your CrewAI manager agent uses this tool to distribute standardized instructions to subordinate agents. This ensures every agent in the crew works with the same updated guidelines. You avoid the drift that happens when agents write their own instructions on the fly.

Dynamic Workspace and Project Context

The `list_projects` tool identifies all active workspaces in your IBM account. A supervisor agent runs this tool at the start of a run to determine where to find the correct models and prompts. Once the supervisor selects the project, the crew executes tasks using models validated by `list_models`. This keeps your multi-agent runs locked to the correct environment.

Setup guide

Set up IBM watsonx 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 IBM watsonx tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass the Vinkius HTTP URL directly into the agent's `mcps` list. CrewAI automatically discovers tools like `generate_text` and makes them available to that agent in your Vinkius MCP setup.

Yes, the server handles concurrent connections from different agents. A research agent can call `generate_text` while an analysis agent runs `generate_embeddings`.

CrewAI monitors token usage across agent steps. It uses the model metadata from `get_model_details` to avoid sending payloads that exceed the context window.

No, Vinkius manages the authentication layer. You configure your IBM Cloud credentials once in your Vinkius dashboard and use a single token in your CrewAI setup.

All agent prompt instructions and intermediate model outputs are processed in ephemeral V8 isolates. The connection uses end-to-end encryption, ensuring your proprietary logic never leaks between agent sessions.

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