How to Use the Nifty MCP in CrewAI

Deploy a CrewAI team to manage Nifty projects for you. Agents can plan milestones, assign tasks, and report on progress autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nifty MCP to CrewAI

Create your Vinkius account to connect Nifty 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 Nifty with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy a Project Manager Crew

Stop managing projects and start managing the system that manages projects. Define a 'Project Analyst' agent that uses `list_workflow_tasks` and `search_all_tasks` to find stalled work. It delegates its findings to a 'Planner' agent. The Planner agent receives the report and decides on a course of action. It might use `create_new_task` to break down a complex problem or `update_task_metadata` to reassign work to someone else. Your agents use Nifty as their shared workspace to get the job done.

Build Autonomous Reporting Agents

Set up a 'Reporter' agent whose only job is to provide status updates. On a schedule you set, it wakes up and uses `list_organization_portfolios` and `list_active_projects` to get a complete overview of the company's work. From there, it can dig deeper with `get_project_details` for key initiatives and compile a summary. This MCP Server provides all the read-only tools an agent needs for deep analysis, before handing off a clean report to a human stakeholder. No manual report generation needed.

Create Self-Healing Task Boards

Your agents can maintain the quality of your project data for you. For instance, a 'Janitor' agent can run hourly, using `search_all_tasks` to find any tasks that are missing a due date or an assignee. When it finds one, it can take action. Depending on its instructions, it might use `update_task_metadata` to flag the task for review, or even assign it to a default team lead. The crew actively prevents messy backlogs through the MCP connection.

Setup guide

Set up Nifty 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 Nifty tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You can use a tool filter when you initialize the MCP tools for each agent. For example, your 'Analyst' agent might only get read-only tools like `search_all_tasks`, while a 'Worker' agent gets `mark_task_as_complete`.

Yes. That's the primary model. Since all agents in the crew are connected to the same Nifty MCP server, they share the same context. One agent can create a task, and another agent can immediately see and modify it.

The easiest way is to pass the Vinkius URL directly into the `mcps` list when defining your Agent in CrewAI. The framework handles the connection and makes all 12 Nifty tools available to that agent automatically.

Yes, that's a perfect use case for a hierarchical crew. You can have a 'Lead' agent that uses `list_workflow_tasks` to monitor a board. When a task is ready for the next step, it delegates the job of calling `mark_task_as_complete` to a subordinate agent.

Your agents can only access Nifty data for the tools you grant them. This MCP server handles project, task, and milestone data. Access is controlled by the Vinkius endpoint token, ensuring your crew can't access anything outside of the defined Nifty tools.

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