Cases / Proof you can check
Real proof, not promises.
Open-source code you can read, a live product we built, and a private enterprise pattern. See how the work holds up before you commit.
Managed Code case studies and open-source work: a public library you can read, a B2C product, and a private enterprise pattern.
- In this collection
- Public gateway library
- B2C product
- Private enterprise pattern
ManagedCode.MCPGateway01
Our open-source engine, out in the open.
We build on our own open-source project. It connects many AI tools and services in one place, lets an AI search across them, and shares only the pieces you choose. Anyone can read the code.
- Official Model Context Protocol C# SDK
- Local and remote tools in one registry
- Prompts, resources, telemetry, and downstream export
Registry · local tools and remote MCP servers
crm.update_record
Localcalendar.book_slot
Remote MCPnotify.customer
Remote MCPOnly the capabilities you choose are passed downstream.
The collection02
Three kinds of proof.
We keep them separate on purpose: public engineering work, a real product for customers, and a clearly labeled enterprise pattern. We do not dress up results we cannot show.
01 / Open source
ManagedCode.MCPGateway
The engine that connects your tools and services for an AI to use. Read the code.
Open the page02 / B2C / Prostir Build
From know-how to a product people use
How we packaged expertise into an AI product for people outside the company.
Open the page03 / Enterprise / Reference pattern
A private, internal AI workflow
Sign-in, limited actions, a visible confirmation, and records your product owns, for work inside a company.
Open the pageWhere this comes from.03
Straight from the official OpenAI and Model Context Protocol documentation.
ManagedCode.MCPGateway
Public repository for the Managed Code MCP Gateway implementation and its current contracts.
02Prostir Build
Managed Code's public B2C AI product for turning expertise into an agent.
03Model Context Protocol · tools specification
Protocol reference for named, discoverable tools and their input and output contracts.
AI / Second opinion04
Not sure where to start? Ask an AI.
Paste this question into ChatGPT, Claude, or Gemini. It walks you through finding the one task your customers would most want to finish by chatting, instead of clicking through your app.
“I run a software product. Help me identify one high-value workflow my customers could finish inside ChatGPT instead of switching between tabs. Ask me about the product, the user, the action, the data it needs, permissions, and the safest small first release.”
The prompt is copied as a backup. Some AI chats may ask you to paste it after sign-in.
FAQ05
Questions, answered.
Is this just an MCP server?
No. The server is one piece. We do the whole job: we pick the customer task, set who can do what, handle the quirks of each AI chat, make the actions run fast, add monitoring, test it, and ship it.
Do we have to rebuild our product?
Almost never. Our layer sits in front of what your product already does. We start with one small workflow and grow from what works.
Will it work in ChatGPT, Claude, and Gemini?
The same build can serve all three. Each one has its own sign-in, look, approval step, and publishing rules, so we set up and test each one separately.
How do you keep it safe?
Your product decides what is allowed, and we keep that in charge. Every action is spelled out, every input is checked, and the customer sees an approval step before anything happens. Our layer sits beside your product, not inside it.
Where does it run? Does it touch our code?
It runs as a separate service in front of your product. It never goes into your code, and you still own your data.
What does it cost, and how fast?
A first workflow starts at €3,200 and goes live in about 7 days.
Contact us06
Now build yours
Send us your product, who uses it, and the action you have in mind. We will tell you the smallest version worth building, and whether it is a €3,200 first workflow or something that needs a closer look first.