Can my AI actively search for a specific customer before creating an invoice?

Yes. It can sequentially execute `search_customers` to find the precise Unique ID of the customer using fuzzy name matching, and subsequently inject that accurate payload into `create_document` without human error.

Is 'list_stocks' showing data in real-time?

Yes. Since this operates as a direct pass-through via the MCP to the PHC GO platform API, all stock matrices, warehouse item counts, and current accounts represent the exact live state of your corporate database in the split second the AI requests it.

Can I query products that exist across multiple warehouses?

Absolutely. By commanding the agent to align returns from both `list_products` and `list_warehouses` against `list_stocks`, your LLM can map out a matrix comparing which warehouse holds the higher volume of the targeted SKUs.

PHC GO MCP Server for Google ADK 16 tools — connect in under 2 minutes

Name: PHC GO
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 16 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add PHC GO as an MCP tool provider through Vinkius and your ADK agents can call every tool with full schema introspection.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token. get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="phc_go_agent",
    instruction=(
        "You help users interact with PHC GO "
        "using 16 available tools."
    ),
    tools=[mcp_tools],
)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About PHC GO MCP Server

Connect your PHC GO enterprise ecosystem to your AI agent and manage operations, invoicing, and logistics through natural language commands natively.

Google ADK natively supports PHC GO as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 16 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

Entity Management — Retrieve master data such as list_customers and natively create_customer directly from your chat context.
Inventory & Logistics — Pull active article sheets with list_products, or audit material counts instantly using list_stocks and list_warehouses.
Billing & Finance — Dynamically execute the create_document endpoint to issue invoices/estimates, and reconcile using list_current_accounts and list_taxes.
Sales Ecosystem — Quickly fetch configuration records like list_series and list_payment_methods to standardize business logic via intelligent agents.

The PHC GO MCP Server exposes 16 tools through the Vinkius. Connect it to Google ADK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect PHC GO to Google ADK via MCP

Follow these steps to integrate the PHC GO MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 16 tools from PHC GO via MCP

Why Use Google ADK with the PHC GO MCP Server

Google ADK provides unique advantages when paired with PHC GO through the Model Context Protocol.

Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with PHC GO

Production-ready features like session management, evaluation, and deployment come built-in. not bolted on

Seamless integration with Google Cloud services means you can combine PHC GO tools with BigQuery, Vertex AI, and Cloud Functions

PHC GO + Google ADK Use Cases

Practical scenarios where Google ADK combined with the PHC GO MCP Server delivers measurable value.

Enterprise data agents: ADK agents query PHC GO and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine PHC GO tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query PHC GO regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including PHC GO

PHC GO MCP Tools for Google ADK (16)

These 16 tools become available when you connect PHC GO to Google ADK via MCP:

create_customer

Criar um novo cliente/entidade no PHC GO

create_document

Criar um novo documento comercial no PHC GO (fatura, orçamento, encomenda, etc)

create_product

Criar um novo artigo ou serviço no PHC GO

get_customer_details

Obter detalhes completos de um cliente/entidade pelo ID

get_document_details

Obter detalhes completos de um documento comercial (fatura, nota crédito, recibo, etc) incluindo linhas

get_product_details

Obter detalhes de um artigo/serviço pelo ID

list_current_accounts

Consultar a conta corrente de clientes (saldos e movimentos pendentes)

list_customers

Listar todas as entidades/clientes registados no PHC GO

list_documents

Listar documentos comerciais do PHC GO por tipo (FT=Fatura, NC=Nota Crédito, RC=Recibo, ORC=Orçamento, ECL=Encomenda, GR=Guia Remessa)

list_payment_methods

Listar métodos de pagamento configurados (Transferência, MB, MBWay, Cheque)

list_products

Listar todos os artigos e serviços registados no PHC GO

list_series

Listar séries de numeração de documentos (FT 2026/, NC 2026/, etc)

list_stocks

Consultar movimentos de stock. Opcionalmente filtrar por artigo

list_taxes

Listar taxas de IVA e impostos configurados no PHC GO

list_warehouses

Listar armazéns configurados para gestão de stock

search_customers

Pesquisar clientes por nome, NIF ou código

Example Prompts for PHC GO in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with PHC GO immediately.

"Check the available stock for 'Macbook Pro M3' across all warehouses."

"Create a new customer profile for 'Acme Corp' and fetch their assigned customer ID."

"Examine our outstanding current accounts from January to spot pending vendor debts."

Troubleshooting PHC GO MCP Server with Google ADK

Common issues when connecting PHC GO to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

PHC GO + Google ADK FAQ

Common questions about integrating PHC GO MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.