How to Use the PHC GO MCP in CrewAI

Q: How do I connect the PHC GO MCP Server to a CrewAI agent?

Pass your Vinkius server URL directly into the agent's mcps array during initialization. CrewAI automatically discovers the 16 tools, including liststocks and createdocument. This allows your specialized agents to call them as needed.

Q: How does CrewAI manage tool access for PHC GO?

You can restrict tool access by using the MCPServerHTTP class with a custom MCP Server filter. This prevents specific agents from executing write tools like createcustomer while still allowing them to read stock levels.

Deploy specialized agent teams with CrewAI and PHC GO to run autonomous billing and inventory audits.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect PHC GO MCP to CrewAI

Create your Vinkius account to connect PHC GO 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 PHC GO with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Run autonomous billing crews with CrewAI

Invoices, receipts, and quotes are written directly to your ERP system via the `create_document` tool. In a CrewAI setup, an Account Manager agent collects client details, while a separate Compliance agent verifies tax rates. Once validated, the acting agent executes the tool to finalize the transaction. By coordinating `list_payment_methods` and `list_taxes` across different agents, your crew ensures that every invoice features the correct payment terms. This division of labor prevents billing errors so you don't have to manually audit invoices. The entire process runs autonomously from start to finish.

Audit stock levels using specialized agents

Real-time inventory movements across your enterprise are compiled by the `list_stocks` tool. A Stock Auditor agent monitors this feed, while a Purchasing agent cross-references the findings with supplier listings. If discrepancies arise, the agents collaborate to resolve them. The auditing agent runs `get_product_details` to verify SKU codes before flagging a shortage. If a product is missing, the purchasing agent uses `create_product` to register the new item. This collaborative loop keeps your physical inventory synchronized with your digital catalog.

Manage ERP customer records via MCP Server

New client profiles and tax identifiers are registered in your central database by the `create_customer` tool. Your CrewAI agent team uses this tool to onboard new sign-ups discovered by a CRM monitoring agent. The agent passes the parsed details to the database writer agent. Before writing, a verification agent runs `search_customers` to check for existing records. If the client already exists, the agent updates the profile using `get_customer_details` instead of creating a duplicate. This ensures your financial ledger remains clean and compliant.

Setup guide

Set up PHC GO 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 PHC GO tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass your Vinkius server URL directly into the agent's `mcps` array during initialization. CrewAI automatically discovers the 16 tools, including `list_stocks` and `create_document`. This allows your specialized agents to call them as needed.

Yes, they can cooperate to manage billing tasks. One agent can query payment options with `list_payment_methods`, another can calculate taxes using `list_taxes`, and a third can execute `create_document` to finalize the invoice.

You can restrict tool access by using the `MCPServerHTTP` class with a custom MCP Server filter. This prevents specific agents from executing write tools like `create_customer` while still allowing them to read stock levels.

The integration supports stdio, SSE, and Streamable HTTP transports. CrewAI connects to your Vinkius-hosted server over these protocols, ensuring fast communication between your agent loop and the ERP API.

Your ERP data, including client tax IDs, stock movements, and financial documents, is isolated within the Vinkius MCP Server sandbox. CrewAI communicates with the server via a single secure token, ensuring no raw credentials leak to the LLM.

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