MCP·Engineering

The SDK wrapper is the easy part.
The production layer is the whole job.

I build Model Context Protocol (MCP) servers — the integration layer that connects AI agents (Claude, ChatGPT, and custom LLM apps) to the APIs, databases, and internal tools they need to actually act on real systems instead of simulating that they do.

Proof you can check before you reply

Public, tested code — not a pitch

Lead with repos and test counts, not adjectives. Every number below is real and verifiable.

179
passing tests in mcp-factory (public)
74
tests in github-mcp — read+write over a real API, public
50
tests in rag-mcp, local embeddings, $0 inference
90s
Loom demo — live test run + auth-scoping + fail-soft

What keeps a server out of the 2am pager rotation

What you get

Most teams know they want their agent wired into their stack. The hard part is building the production layer correctly — and that is the whole job.

A working MCP server

Scoped to your specific tools and APIs, with typed tool definitions an agent can call reliably.

Auth-scoped

At the right trust boundary — API-key, OAuth, or session-scoped — so an agent can't read across the wall.

Fail-soft

Backend-down, rate-limit, timeout — each returns a clean structured error. The agent session lives.

Version-pinned

So an upstream API change doesn't silently break the integration weeks after handoff.

Tested

Runs green on a clean checkout — not a demo that breaks on the second request.

Documented for handoff

Your team can extend the server without the original author. No bus-factor of one.

Fixed-scope, not open-ended hourly

The offer

Every engagement is scoped and quoted flat. Start with a low-risk audit; the fee credits toward the build if you proceed. A typical Sprint ships a working, tested server in about two weeks.

Proposed pricing. These tiers are a starting point pending confirmation — the final tier is set after a scoping call, because I don't quote before I understand the build.
MCP Readiness Audit
$1,500 / 3 days
Entry point — written report, no code.
  • A read of your stack and integration surface
  • An MCP spec + risk log so you ship the right server first
  • Credited in full toward a Sprint within 60 days
Start with an audit
Multi-Source / Retainer
$12k+ / or $2–3k mo
Enterprise build, or keep it green after.
  • Multi-tenant, self-hosted / on-prem, regulated stacks
  • Retainer: tests stay green, tool updates, one new tool/mo
  • So your team doesn't have to care about the plumbing
Talk scope

How an engagement runs

Process

A short paid spike de-risks the build before either of us commits to a fixed quote.

01 — SPIKE

Audit & scope

A read of your stack delivered as a written MCP spec + risk log. You ship the right server the first time; the fee credits toward the build.

02 — BUILD

Fixed-scope sprint

~1–2 weeks. Auth-scoped, fail-soft, version-pinned, tested. You see it run green on a clean checkout — not just on my machine.

03 — HANDOFF

Documented delivery

Handoff docs so your team extends the server without me. Optional retainer keeps it green as upstream APIs and the MCP spec change.

How I work, shown in real builds

Case studies

No fabricated client wins. These are my own public, tested builds — and an honest look at how I validate (and kill) systems.

// mcp-factory

Browse the proof before you reply

A manifest-driven MCP scaffolder + runtime. 179 passing tests, public repo, 90-second Loom demo of a live test run.

Read the case study →
// github-mcp

Read+write over a real external API

The exact common client ask: a read/write MCP over the GitHub REST API. Write tools off by default, typed rate-limit handling, 74 passing tests, public repo.

Read the case study →
// desktop-mcp

Range, past the API layer

OS-level control when there's no API: screenshot, windows, input, screen-recording. Input off by default, rate-capped, 121 passing tests, public repo.

Read the case study →
// rag-mcp

A real, citation-backed MCP server

Retrieval-augmented search exposed as an MCP tool. Local ONNX embeddings, fail-soft, 50 tests, $0 inference cost.

Read the case study →
// honest validation harness

I kill what doesn't clear costs

The reliability story: how I forward-test systems honestly and retire the ones that don't earn their keep. Rigor, not returns.

Read the case study →

Before you reach out

FAQ

Do you work hourly?

No. Work is fixed-scope sprints, scoped and quoted flat after a short call. The entry point is a $1,500 MCP Readiness Audit (written report, no code), credited toward a Sprint if you proceed within 60 days.

How long does a Sprint take?

A typical Integration Sprint ships a working, tested server in about two weeks. Multi-source and self-hosted builds are larger and scoped separately.

What if I already have an MCP server?

The audit covers that too — a read of the existing server for auth-scoping gaps, fail-soft handling, version-pinning, and test coverage, delivered as a written risk log. The MCP spec is still moving; existing servers will need updates as it changes.

What stack do you support?

Python and Node MCP servers over REST, on cloud or self-hosted / on-prem. Auth via API-key, OAuth, or session-scoping. If your tools speak HTTP, they can be wired.

Can I see proof before committing?

That's the whole point. mcp-factory is public with 179 passing tests, and there's a 90-second Loom demo showing the test run, auth-scoping, and fail-soft handling live.

Do you have client testimonials?

Not yet — and I won't fabricate any. Instead I publish tested code you can check yourself and a case study on how I validate systems honestly (including killing ones that don't work). That's the trust signal, in place of borrowed logos.

Wire your agent into the real thing

Send me the two or three tools you need an agent to actually use. I'll tell you the right scope and a flat quote — after I understand the build, not before.

Book a scoping call