How to Use the ONES MCP in CrewAI

Q: How do I connect ONES to my CrewAI setup?

Install crewaitools. Pass your server URL directly into the mcps array when defining your agent, and the tools will auto-register.

Q: How do I restrict ONES tool access in CrewAI?

Import MCPServerHTTP from crewai.mcp and use the toolfilter parameter. This lets you give one agent read-only access while another gets write permissions.

Deploy specialized agent crews that autonomously manage your ONES R&D projects, triage bugs, and assign tasks using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect ONES MCP to CrewAI

Create your Vinkius account to connect ONES to CrewAI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup ONES with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Triage projects autonomously

The ONES MCP Server gives your Python-based agents direct read-write access to your engineering backlog. You can assign a researcher agent to constantly poll `list_tasks` and look for untriaged bugs. When it finds a new issue, the agent pulls the full context via `get_task_details` and `get_project`. It stores this context in CrewAI's shared memory, allowing the next agent in the sequence to make an informed decision.

Route tickets intelligently

Through the MCP Server, a separate manager agent takes the researcher's findings and decides who should fix the bug. It runs `list_members` to check the current roster and matches the required skills. Once a developer is selected, the agent executes `update_task` to assign the ticket. It also checks `list_workflows` to ensure the ticket moves correctly from the triage state to active development without violating any enterprise rules.

Synchronize across projects

Large organizations often struggle with dependencies across different teams. A moderator agent can monitor `list_projects` to spot blockers across multiple R&D streams. If a blocker is identified, the agent autonomously triggers `create_task` in the dependent team's board. It uses `get_org_info` to format the request properly, keeping your entire engineering department aligned without manual status meetings.

Setup guide

Set up ONES 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 ONES tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Install `crewai[tools]`. Pass your server URL directly into the `mcps` array when defining your agent, and the tools will auto-register.

Yes. When your researcher agent reads a ticket, CrewAI saves that data in shared memory so the execution agent knows exactly what to do.

Import `MCPServerHTTP` from `crewai.mcp` and use the `tool_filter` parameter. This lets you give one agent read-only access while another gets write permissions.

They will if you configure them to run autonomously. For safer operations, you can set up a hierarchical crew where a manager agent requires human validation before acting.

Your agents will process sensitive R&D metadata, including bug reports, project roadmaps, and organization member lists. This MCP integration relies on secure endpoint tokens, ensuring your local Python environment is the only entity executing calls.

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