Model Context Protocol
Hire MCP developers who give assistants tools, not keys
Our engineers built commitment-tracking into Go4Gr8, a live coaching platform, deciding what the assistant may touch before wiring a single call.
What you are getting
4 things that decide this
- 01Senior engineers with MCP tools already running in production, not a weekend experiment with a protocol they read about.
- 02They scope permissions first. An assistant gets the narrowest tool that does the job, never a general key to your systems.
- 03You interview every engineer before they join, and they work in your repo and your standups rather than behind a ticket queue.
- 04You own the server, the tool definitions and the audit trail from the first commit. Interview anyone we put forward, and decline anyone who isn't right for the boundary.
The boundary is the whole job
The Model Context Protocol is an open standard for connecting AI applications to your systems. Its own documentation calls it a USB-C port for AI: one way to plug a model into data and tools, supported by Claude, ChatGPT, VS Code and Cursor.
Writing a server that lists a tool is a short afternoon. The engineering is in the boundary. On Go4Gr8, the assistant tracks the commitments a leader makes during coaching, through MCP tools, inside a multi-tenant platform where each user has their own agent. The tool can record a commitment for that user. It cannot read another organisation's coaching history. The permission is decided in the server, not requested in a prompt.
That is the difference worth paying for. A prompt is a suggestion. A permission is a rule.
What they decide before a single tool is written
Tools scoped to one job
A tool that books an appointment, not a tool that runs SQL. Narrow definitions are what stop a confused model doing damage.
Identity carried through
The assistant acts as a specific user, with their permissions. Without this, every request runs as an administrator by accident.
Actions that are safe to repeat
A retried tool call must not charge a card twice. Idempotency keys make a repeat safe instead of expensive.
An audit trail per call
What was called, by whom, with what arguments, and what came back. This is the first thing anyone asks for after an incident.
Evals on the tool layer
A scored set of cases checking the assistant picks the right tool. Model upgrades change behaviour, and this is how you find out first.
- AssistantAsks for a tool
- MCP serverYour code, your rules
- IdentityActing as which user
- PermissionAllowed, or refused here
- SystemThe call finally lands
Everything that matters happens in the middle three boxes. A server that only forwards the request has moved your security into a prompt.
“They have a problem-solving mindset, analytical skills, and deep technical knowledge.”
David Manley · CEO, Go Real Travel
How hiring works
- 01
Tell us what the assistant must reach
A free call about the systems it touches and the actions you would never want it taking. If a plain API is enough, we say so and you have lost nothing.
- 02
Meet the engineers
We shortlist people who have drawn a permission boundary before, and you interview them yourself. Turn any of them down without explaining why.
- 03
They embed
Your repo, your standups, your environments. One of our engineers owns the boundary design and answers for it by name.
- 04
They hand over
Tool definitions, the permission rules and the eval set, with someone on your team trained to extend them. Some clients keep us on the pager instead, under a service level we agree. The first 2 months of support and maintenance are free, with every build.
Stack
Protocol and models
- Model Context Protocol
- Claude
- OpenAI GPT-4o
- Tool calling
- LangGraph
Around it
- FastAPI
- Python
- TypeScript
- PostgreSQL
- WebSockets
- AWS
Practices
- Scoped tool definitions
- Idempotency keys
- Per-call audit logs
- Scored eval sets
Tell us what you will not let an assistant do
Bring the systems it needs to reach and the actions that scare you. The scoping call is free, and the boundary is the first thing we design.
01How is hiring an MCP developer different from posting the role on a job board?+
A job board hands you a resume claiming MCP experience. We hand you an engineer who has already drawn a permission boundary in a live multi-tenant product, and you interview them yourself before anything starts. You work in their standups, not through a ticket queue.
02What stops the assistant doing something expensive or destructive?+
The server refuses it. Permissions are checked in your code before the call reaches the system. Dangerous actions are never exposed as tools at all, and anything costly sits behind a human approval step. On Go4Gr8, commitment tracking runs inside a multi-tenant boundary for this reason.
03What if the engineer turns out to be the wrong fit for our stack?+
Say so and we replace them. You interviewed them before they started, and the same standard applies mid-project: nobody stays on a repo where the fit is wrong for either side.
04What hours do MCP developers work, and how much overlap do we get?+
We agree a real overlap window with your team before the engineer starts, not after. Server and permission design benefits from live back-and-forth with whoever owns the systems it touches, so overlap is set to make that possible, not left to chance.
05Who owns the server, the tool definitions and the permission rules afterward?+
You do, from the first commit. The code lives in your repository, the audit trail is yours to query, and nothing about the tool layer depends on us staying involved.
06What decides the cost of an MCP build?+
Three things: how many tools you need, how many systems sit behind them, and how clearly your permission rules are already written down. A team that can say who may do what is cheaper to build for than one discovering it during the work. Scoping calls cost nothing. Every build starts with a fixed-fee Blueprint: an engineer reads your real systems and writes the plan, with a fixed price for each milestone rather than a guess. The fee is credited in full against the build, and if the plan isn't one you'd act on, you don't pay for it.
Read next
- what MCP is →The standard, its primitives and both transports.
- an MCP server in production →Commitment tracking, multi-tenant.
- AI agent development →When we build the agent instead of staffing it.
- hire AI agent developers →The wider agent role.
- best MCP servers to run →Ranked on maintainer, auth model and how each one fails.
