AI Agent Tools & MCP Servers
Letting AI use the software you already have
Your existing software opened up as tools an AI agent can call, without rewriting anything that already works.

Photo: Pexels / Pixabay 
Photo: francescobovolin / Pixabay
Selected work demonstrating this service.
-
Designed a JSON passthrough from Postgres to API
Designed a JSON passthrough architecture where PostgreSQL functions return complete JSON forwarded verbatim by the Go API, eliminating intermediate unmarshalling and decoupling the frontend from schema changes.
-
Migrated the API to Huma v2 at 100% parity
Migrated the HTTP API from Fiber to Huma v2 — 649 paths and 760 operations — reaching and holding 100% parity between the routes the server registers and the OpenAPI description it publishes.
-
Generated the API contract from the database out
Generated the API contract outward from the database — OpenAPI, a 44,076‑line typed TypeScript client, 61 mock handlers and the limits the UI enforces — with a guard at every hop that fails on drift.
-
Moved slow work onto a River job queue
Moved slow work off the request path onto a River job queue — 15 worker modules, 8 scheduled tasks and 20 pg_cron jobs — so a request returns while the work behind it carries on.
-
Built the operator back‑office for the platform
Built the operator back‑office — around 40 admin routes and 128 components covering claims, moderation, feature flags, cache and diagnostics — so the platform can be run without database access.
If this is the work you need done, the next step is a conversation.
Tell us the problem and we will tell you honestly whether we are the right people.

