— Practice / MCP
MCP server development.
The Model Context Protocol is how AI agents call your software as tools — search your data, run an action, complete a task. We design and build production MCP servers on Cloudflare Workers: fast, globally distributed, and hardened for real use, not a demo.
— Why us
We run the thing we sell.
This site has a public MCP server you can install in Claude or Cursor right now, and we publish an open-source MCP template that other teams deploy. We build MCP servers for clients the same way — with the production hygiene most starters skip.
Install it: add https://setkernel.com/mcp to Claude Desktop or Cursor — no auth needed. The server card is at https://setkernel.com/.well-known/mcp.json.
— What we build
From one tool to a full agent surface.
Tool servers
Expose your systems — a database, an internal API, a search index, a booking flow — as MCP tools an agent can call safely, with input validation and rate limits.
Streamable HTTP transport
Modern remote MCP over HTTP (the transport Claude and Cursor use), deployed on Cloudflare Workers so it scales to zero and runs close to every user.
Auth and access control
Bearer tokens, OAuth, or fully public — scoped to what the tools actually need, with the audit trail and revocation you need to run it in production.
Grounded retrieval
Pair the server with a RAG pipeline so agents answer from your own content with citations, not guesses. We build both halves.
Evals and guardrails
The parts that keep an agent honest in production — tests on tool behaviour, structured logging, and the observability to see what agents actually did.
Server card and discovery
A published server card and the well-known discovery surfaces so agents and directories can find and describe your server without a human in the loop.
— How it works
The engagement.
Same five-step method as every SetKernel build — Brief, Architect, Sprint, Ship, Operate — each with a written artefact you review. We start from a short written brief: which systems the agent should reach, who should be allowed to call them, and what done looks like. You get a scoped price and a fit / no-fit answer within one business day.
— Where we work
Atlantic Canada, and worldwide.
We are a complete technology partner in Halifax, Nova Scotia, Canada, and we work remotely with teams well beyond the region. MCP is transport-agnostic and cloud-native — where your team sits does not change the build.
— Questions
Before you write.
What is an MCP server, in one sentence?
A Model Context Protocol server exposes your software as a set of tools that an AI agent — Claude, Cursor, ChatGPT, or any MCP client — can call to look something up or take an action, over a standard protocol so you build it once and every client works.
Why build it on Cloudflare Workers?
Workers scale to zero, run in every region by default, and have no cold-start tax — so an MCP server costs almost nothing at rest and stays fast under load. It is also where we do our deepest work, so you get platform-native engineering rather than a lift-and-shift.
Do you only build the server, or the agent too?
Either. Some clients have an agent and need a server to give it tools; others want the whole system — server, retrieval, evals, and the agent that uses them. We scope to what you actually need.
Can we see your work first?
Yes. Install the MCP server that powers this site, read the open-source cf-mcp-template, and its companion essay on running MCP in production. We would rather show you working code than a pitch.
How do we start?
Send a short written brief — the systems the agent should reach, who may call them, and the deadline. We reply in writing within one business day with fit / no-fit and, if fit, a scope and price. No discovery call before the brief.
— Engage
Have something you want an agent to be able to do?
Tell us in two paragraphs — the systems, the callers, the deadline. We reply in writing within one business day.