How to Use the AccuLynx MCP in CrewAI

Q: How do I expose AccuLynx tools to CrewAI?

Install crewaitools via pip. You can pass the Vinkius URL straight into the mcps array on your Agent definition. The crew will automatically discover the roofing tools.

Q: Can I restrict which CrewAI agent sees AccuLynx payments?

Yes, use MCPServerHTTP from crewai.mcp. Apply a toolfilter so only your finance agent can access the listpayments function. Your lead generation agents won't even know it exists.

Deploy a team of autonomous agents to manage your roofing business. CrewAI connects directly to AccuLynx to monitor jobs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AccuLynx MCP to CrewAI

Create your Vinkius account to connect AccuLynx 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 AccuLynx with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign AccuLynx tasks to CrewAI agents

One agent cannot run a whole contracting business. You spin up a researcher agent to monitor `list_leads` for new inquiries. When it spots a fresh prospect, it hands the data off to a sales agent. The sales agent then executes `create_lead` using the extracted first and last names. This sequential execution mimics how a real front office works, completely autonomously.

Monitor job milestones hierarchically

Project managers need constant updates on roofing installations. A dedicated monitor agent polls `get_job_details` using specific job IDs. It analyzes the technical metadata and drops a summary into shared memory. A moderator agent reads that memory. If a job falls behind schedule, it escalates the issue. The MCP Server acts as the direct bridge between your Python logic and the project data.

Audit cash flow continuously

Financial oversight requires a specialist. You assign a billing agent exclusive access to the `list_payments` tool. It scans open jobs and tallies up the collected revenue without distracting the other agents. CrewAI handles the tool filtering natively. You use MCPServerHTTP to ensure only the billing agent sees the financial endpoints, keeping your multi-agent architecture strictly scoped.

Setup guide

Set up AccuLynx 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 AccuLynx tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Install crewai[tools] via pip. You can pass the Vinkius URL straight into the mcps array on your Agent definition. The crew will automatically discover the roofing tools.

Yes, use MCPServerHTTP from crewai.mcp. Apply a tool_filter so only your finance agent can access the list_payments function. Your lead generation agents won't even know it exists.

The framework relies on shared memory. When one agent fetches technical milestones, it logs the context. Subsequent agents read that history instead of making redundant API calls.

The Python implementation supports stdio, SSE, and Streamable HTTP. The MCP Server handles the connection natively, so you just provide the endpoint token and let the agents run.

Not a chance. Vinkius isolates the entire connection in a stateless sandbox. Your roofing payment histories pass through an ephemeral tunnel directly to the authorized agent, leaving zero trace behind.

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