How to Use the Qualified.io MCP in CrewAI

Q: How do my CrewAI agents invite candidates to a Qualified.io assessment?

Your recruiter agent uses invitecandidates or invitecandidatesviacohort when a new applicant enters your pipeline. The agent handles the dispatch autonomously based on the candidate's profile.

Q: Can CrewAI write candidate reviews directly inside Qualified.io?

Yes, your grading agent uses createassessmentresultreview to write detailed feedback. The agent posts this review directly to the candidate's test file once it finishes analyzing their code submissions.

Q: How do we handle test retakes with Qualified.io and CrewAI?

Your moderator agent calls scheduleretryassessmentresult to reopen access for a candidate. The CrewAI coordinator then notifies the candidate that their test window is open again.

Q: Can agents archive old tests using this MCP Server?

Yes, your content agent monitors test usage. It calls archiveassessment to retire challenges that no longer match your current engineering hiring standards.

Deploy a crew of specialized AI agents to manage, grade, and review your Qualified.io technical assessments with CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Qualified.io MCP to CrewAI

Create your Vinkius account to connect Qualified.io 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 Qualified.io with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Run autonomous screening crews with this MCP Server

The `list_assessments` tool allows your CrewAI coordinator agent to audit your active Qualified.io test library. This CrewAI agent identifies which coding tests are published in Qualified.io and passes that list to your recruiter agent. Once the active tests are confirmed, the CrewAI recruiter agent uses `invite_candidates` to dispatch Qualified.io invites. This CrewAI collaboration ensures you never invite candidates to outdated or unpublished Qualified.io tests.

Audit candidate performance using CrewAI teams

The `get_assessment_result` tool feeds raw candidate performance data directly to your CrewAI grading agent via our MCP connection. This CrewAI agent analyzes the Qualified.io code submissions, execution times, and test pass rates. If the CrewAI grading agent flags an anomaly, it hands the task to a moderator agent that runs `get_assessment_result_exhibit` to inspect the detailed Qualified.io test output. The CrewAI team works together to verify candidate work in Qualified.io before sending it to human reviewers.

Maintain your challenge library autonomously

The `list_challenges` tool gives your CrewAI content curator agent a full view of your Qualified.io coding tasks. Our CrewAI agent evaluates Qualified.io challenge performance metrics to identify outdated or overly difficult questions. When a bad challenge is found, the CrewAI curator agent uses `archive_assessment` to pull it from active Qualified.io rotation. It then calls `create_assessment` to replace it with a fresh, updated coding problem inside the Qualified.io library.

Setup guide

Set up Qualified.io 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 Qualified.io tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Your recruiter agent uses `invite_candidates` or `invite_candidates_via_cohort` when a new applicant enters your pipeline. The agent handles the dispatch autonomously based on the candidate's profile.

Yes, your grading agent uses `create_assessment_result_review` to write detailed feedback. The agent posts this review directly to the candidate's test file once it finishes analyzing their code submissions.

Your moderator agent calls `schedule_retry_assessment_result` to reopen access for a candidate. The CrewAI coordinator then notifies the candidate that their test window is open again.

Yes, your content agent monitors test usage. It calls `archive_assessment` to retire challenges that no longer match your current engineering hiring standards.

Absolutely, because Vinkius runs ephemeral execution environments where candidate developer profiles and scores are never logged. Your CrewAI team communicates with Qualified.io using zero-trust credentials running inside our secure MCP sandbox.

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