Cases / Public proof and reference patterns
Read the public MCPGateway case, then compare the B2C Prostir Build product with a private enterprise implementation pattern.
↓ManagedCode.MCPGateway
The open-source .NET library combines local AI tools and remote MCP servers, supports graph and vector search, and exposes selected capabilities downstream.
Collection / cases
The library distinguishes public engineering proof, a real B2C product, and a clearly labelled enterprise reference pattern. It does not invent client outcomes.
03A searchable execution surface for local tools and remote MCP servers.
Open the page↗B2C / Prostir Build02How Managed Code’s B2C product packages knowledge for people who use it outside the organization.
Open the page↗Enterprise / Reference pattern03Identity, scoped tools, visible confirmation, and product-owned records for internal work.
Open the page↗Public repository for the Managed Code MCP Gateway implementation and its current contracts.
Managed Code's public B2C AI product for turning expertise into an agent.
Protocol reference for named, discoverable tools and their input and output contracts.
AI / Second opinion
Use this prepared question to assess where an AI Product Interface could remove friction from your product.
“I run a software product. Help me identify one high-value workflow customers could complete through an AI Product Interface. Ask me about the product, the user, the action, required data, permissions, and the safest small first release.”
The prompt is copied as a backup. Some AI hosts may ask you to paste it after sign-in.
No. The MCP layer is one part. We also scope the product actions, permissions, host-specific behavior, UI, testing, and release path.
Usually no. The interface sits in front of approved capabilities in your existing product. We start with a narrow workflow and expand from evidence.
The shared architecture can support all three. Each host still has its own UI, authentication, approval, and publishing rules, so we verify them separately.
We define explicit tools, validate inputs, keep user approval visible, and preserve the product's existing authorization rules.