From the PMC teamDevelopment projects start in 2027. Plan yours now to secure an early start.

Integrations and MCP

One connection to every system. And to your AI.

Every system names the same data differently. We build the integration layer that translates between them, and MCP servers that let AI assistants work with your data, with permissions and a log of every call.

  • Fast to deliver
  • Built to last
  • Secure from day one
11+years of building software for finance, IT and project teamsAbout the team
Integrations and MCP

Our integration and MCP services

One shared data model between your ERP, CRM, HR and finance systems, and MCP servers that open it safely to your AI assistants.

ERP integration

SAP and other ERP systems connected to your applications in both directions.

Discuss this service

What we cover: Any system with an API, a database or a file export: ERP, CRM, HR, finance or your own software. Where no connector exists we write it, and we build MCP servers for any tool your AI assistants should use.

The team behind PMC, trusted by
  • BNP Paribas
  • Allianz
  • Hexagon
  • Hewlett Packard Enterprise
  • Enapter
Solutions

Integrations we build

  • ERP to budget control

    Purchase orders, goods receipts and invoices flow from SAP into PMC on a fixed schedule.

  • An assistant on your data

    Employees ask an AI assistant about contracts, tickets or stock, and it answers from your systems.

  • HR in sync

    Employees, departments and cost centres stay the same in HR, IT and finance.

  • An API for your partners

    Your product offers a documented interface that customers and partners can connect to.

Your systems still exchange data by export and e-mail?

List the systems and the files that travel between them. We sketch the interfaces and the data model that replace them.

Plan your integration
A worked example

How a project like this runs.

Example

Purchase orders from SAP into budget control

The situation

Controllers export purchase orders and invoices from SAP every week and copy them into project budgets, so the figures are always a week old.

What we do
  1. We list which fields live where and how SAP and the budget tool name them.

  2. One data model agreed with controlling and IT, cost centres and project codes included.

  3. An interface moves orders, goods receipts and invoices on a fixed schedule, checked at the border.

  4. Transfers are watched on a dashboard; failures are retried and reported to IT.

The result

Budgets show committed and actual costs from SAP without manual exports.

An illustrative example of the way we work, not a named customer.

AI inside

AI on your connected systems

Through MCP servers that give each assistant only what its user may see.

  • MCP servers for assistants
  • Questions on live ERP data
  • Search across systems
  • Data mapping suggestions
  • Interface error analysis
  • Logged, permissioned calls
  • Documents matched to records
  • Reports across systems
  • Write-back with approval
Why it pays

Why connect your systems properly

01

One data model for every report

Today
The same supplier, cost centre or project under a different name in every system.
With it in place
One shared data model that every system and every report uses.
Reliable by design

Data you can rely on, every time it moves.

How an integration keeps working long after go-live.

Checked at the border
Incoming data is validated against the shared model before it reaches your systems.
Only the access it needs
Each connection gets only the rights it needs, and credentials are stored outside the code.
Nothing lost on failure
Failed transfers are retried and reported, so no record disappears without a trace.
AI access under control
MCP tools respect each user's permissions, and every call is logged.
What you receive

Everything you need to own the result.

  • Interfaces running in your environment or ours
  • The shared data model, written down field by field
  • An OpenAPI description of every interface we build
  • MCP servers with permissions per user, where AI is involved
  • A monitoring dashboard and alerts for failed transfers
  • Documentation your IT can maintain

Is it right for you?

A good fit when
  • Two or more systems that hold the same data in different forms
  • Reports that need figures from several systems
  • AI assistants that should work with live data from your systems
Not the right fit when
  • Systems with no API, no database access and no export at all
  • A one-time transfer that will never run again
Speed, quality and security

Fast does not have to mean fragile.

Every project is held to the same standard, whatever the service. It is the standard we build and run PMC to every day.

  • Fast to deliver

    Results in weeks, not quarters.

    • A working version at the end of every short cycle
    • Releases through an automated pipeline, not by hand
    • Small changes shipped often, so value arrives early
  • Built to last

    Software your team can still understand and change years from now.

    • Every change built and tested automatically before it is merged
    • Unit, API and end-to-end tests in a real browser
    • Documentation and a clean handover, or we run it for you
  • Secure from day one

    Security is part of the build, not a check at the end.

    • OWASP Top 10 and BSI IT-Grundschutz as the reference
    • Dependencies and images scanned for known vulnerabilities in every build
    • Access by role, changes logged, secrets kept out of the code
How we work

From scattered systems to one connected picture.

  1. Map systems and fields

    We list which data lives where and how each system names it.

  2. Agree one data model

    Fields from every source are mapped to one model that your teams and your AI share.

  3. Connect and test

    Interfaces are built in both directions and tested with real records.

  4. Monitor in operation

    Transfers are watched on a dashboard; failures are retried and reported.

Interfaces that break and nobody notices?

We put monitoring, retries and a status dashboard on what you have, and replace what cannot be saved.

Review your interfaces
Ways to work with us

Choose how much of the work you hand over.

From one clearly scoped project to a team inside your business and the long-term running of what we built. Every model has one accountable partner: Virtual Eye.

  • For a defined result

    Fixed-scope project

    You know what you get before the build starts: a concept, a prototype and a fixed scope come first.

    • A workshop on your process and the result you need
    • Concept, prototype and fixed scope before production code
    • A working version at the end of every short cycle
  • When the problem is not yet clear

    Forward deployed team

    A small Virtual Eye team works inside your business, learns how work and money really move, and delivers the solution with your people.

    • One lead for management, plus the engineers who build
    • Outcome and scope agreed in writing
    • A demo every week
  • For software you already run

    Takeover and modernisation

    We take over an existing application, make it safe to change, then develop it further step by step.

    • What exists is documented and tested first
    • Stabilised before anything new is added
    • Further development in small, tested releases
  • After go-live

    Run and evolve

    We host, monitor, update and support your applications on our servers, in your cloud or on-premises.

    • Monitoring and alerts that go straight to our team
    • Backups, updates and security patches
    • Support and further development from the team that built it
Customers

What customers say about working with us.

Quotes about the Virtual Eye team from PMC projects: the same people who would work on yours.

“Well thought-out concepts, tailored precisely to us. Very competent and always friendly, even during the stressful implementation phase.”
Iris HummelManager Infrastructure Services Sales DACH, Hewlett Packard EnterpriseTranslated from German
“PMC provides valuable support in day-to-day business and the team is very reliable, serious and friendly!”
Hao LiCentral Project Office PMO, Allianz Global Corporate & Specialty SE
“As a customer from day one, we have found reliable, fitting solutions with Virtual Eye throughout the years. Above all, the fast and flexible service.”
Sebastian StepferExecutive Director Public Safety EMEA Region, HexagonTranslated from German
Tech stack

The tools we use for this.

We choose them for your systems and your team, and we document every choice.

Messaging, APIs, identity and process engines that let your systems work as one.

Messaging and streaming

  • Apache Kafka
  • RabbitMQ
  • ZeroMQ
  • NATS
  • Apache ActiveMQ
  • IBM MQ
  • Azure Service Bus
  • Azure Event Hubs

Authentication and access control

  • OAuth 2.0
  • JWT
  • OpenID Connect
  • Keycloak
  • Auth0

APIs and communication

  • REST
  • SOAP
  • GraphQL
  • WebSockets
  • gRPC
  • RSocket
  • OpenAPI
  • Model Context Protocol

Workflow and process automation

  • Camunda
  • Activiti
  • Zeebe
  • jBPM
  • Flowable
Your technology is not listed?

Tell us what you run. If we have not worked with it yet, we say so, and tell you how we would approach it.

Talk to our engineersSee all technologies
Industries we serve

Integrations for the industries we know

Years of PMC have taught us how these industries approve, buy, report and get audited.

Banks

Interfaces between core banking, finance and controlling, documented for audit.

  • Finance and controlling feeds
  • Logged, permissioned APIs
  • Reconciliation reports
Questions

Questions teams ask before they start.

What is MCP?

The Model Context Protocol is an open standard that lets AI assistants such as Claude or ChatGPT use tools. An MCP server turns your systems into such tools, with the permissions you set.

Our system has no API. Can you still connect it?

Usually yes: through database views, scheduled file exports or the interfaces the vendor offers. We choose the most robust way your system allows.

Who looks after the integration?

We can run and monitor it for you, or hand it over to your IT team with documentation and tests.

How do you keep the data consistent?

Fields from every source are mapped to one data model, and incoming data is validated against it before it reaches your systems.

Is it safe to give AI assistants access to our systems?

MCP tools respect each user's permissions, each connection gets only the rights it needs, and every call is logged.

Tell us what you want to build.

Describe the process, the systems involved and when it should go live. We reply with a first assessment and the next step.

Or write to us directly: hello@virtual-eye.com

What happens next?

  1. You write to us

    What you want to build, the systems involved and when it should go live.

  2. A first assessment

    We reply with a first assessment and the next step.

  3. A workshop

    On your process and the result you need, before any technology is chosen.

  4. A fixed scope

    A concept, a prototype and a fixed scope before the first line of production code.