Model Context Protocol specialists
Deep skills without product context tend to produce fragile integrations. The specialist work has to connect to real user flows.
We document the prompts, tools, schemas, and day-to-day runbooks so your team can run the system after we hand it over.
Most people who reach this page are teams adopting agentic AI tooling. Custom MCP servers that connect AI agents to your tools, data, and workflows.
What you get
- Custom MCP server development
- Tool-calling integrations
- Secure agent access patterns
- Cursor and Claude-ready tooling
- One studio accountable for the result
- Design and engineering on the same schedule
- Support available after launch
How engagement works
As your MCP developer, we run a shared backlog, design reviews, and engineering sprints, and you keep one point of contact throughout.
- 01
Discover
Goals, constraints, data sources, and success metrics, all settled before we touch architecture or prompts. The work for remote and worldwide teams stays tied to the outcome you asked for.
- 02
Design
System design, AI/tool boundaries, interface direction, and interaction prototypes. You see progress on the critical path every week.
- 03
Build
Modern stack, clean architecture, evaluated AI behavior, and iterative demos you can react to. Nothing here waits on a handover between separate teams.
- 04
Launch
Ship, monitor, harden, and keep improving models, tools, and product after go-live. On MCP development projects we favour practical architecture over trendy defaults.
How we build it, and why
The stack is chosen per project, not applied from a template. For MCP developer work these are the defaults, and the reason each one is on the list.
- MCP
- the Model Context Protocol, so your tools plug into Claude, Cursor, and other agent clients without a custom adapter for each
- TypeScript
- types across the whole stack, which catches the class of bug that only shows up in production
- Node.js
- one language across the stack, so context does not get lost at the boundary
- Claude
- long-context reasoning and reliable tool calling for agent work
- OpenAI
- a second model provider, so a single vendor's outage or price change is not your problem
What the first weeks look like
- Week 1
Spike the risky part
We build the thinnest possible version of custom mcp server development against your real data. If it is going to be a problem, it is better to know in week one than week six.
- Weeks 2-3
Harden the integration
Auth, rate limits, error paths, and the data contract. This is the work that separates a demo from something you can leave running.
- Weeks 4-6
Wire it into the product
The MCP development stops being a standalone service and becomes a feature people use, with the interface and permissions that implies.
- Ongoing
Evaluate and tune
Behaviour gets measured against cases you care about, and we tune from that rather than from impressions.
Weighing up your options
There are three realistic ways to get this built. Each is the right answer for someone.
A solo freelancer
Cheapest per hour and fine for a contained task. The risk on MCP development is breadth — one person covering design, backend, infrastructure, and launch usually means one of them is weak, and there is no cover when they are unavailable.
An in-house hire
A permanent engineer is the right call once the MCP development is continuous rather than a project. Before that point you are paying a salary, recruiting for months, and carrying the risk that the first hire is the wrong shape for the problem.
Arcode
A small senior team. The people who scope the MCP development write the code, you get weekly demos instead of status decks, and the engagement ends when the thing is live and handed over.
Work we have shipped
Note Assist
AI product · Next.js · Speech
AI meeting assistant with live speech-to-text, ChatGPT chat, and Firebase auth for transcription workflows.
Freelance AI product built with Next.js, Firebase, AssemblyAI, and ChatGPT for live meeting transcription and realtime chat around the transcript.
- · Live speech-to-text transcription
- · Realtime chat over meeting notes
- · Firebase authentication
- · AI-assisted follow-up on transcripts
Next.js · Firebase · AssemblyAI · ChatGPT · TypeScript
Case Management Hub
Full-stack engineer · NestJS · Next.js
HIPAA-compliant healthcare SaaS for 150+ US organizations, with dual databases, realtime collaboration, billing, and secure client portals.
Enterprise case management platform for healthcare and social-work organizations with encryption, realtime messaging, Stripe billing, Zoom, and calendar sync.
- · HIPAA-ready architecture with encryption and audit logging
- · Realtime collaboration via Socket.io + Redis
- · Client portal and role-based access control
- · Stripe billing and document workflows
Next.js · NestJS · TypeScript · MongoDB · Redis · Socket.io
Circlin Waitlist
Lead frontend · Next.js 15
Multilingual waitlist and referral product for a secondhand fashion brand, covering localization, analytics, and growth loops.
Waitlist experience with EN/DE localization, referral tiers, MDX blog, and analytics for Circlin.
- · EN/DE internationalization
- · Referral reward tiers
- · MDX blog and SEO content
- · Analytics and cookie consent
Next.js 15 · TypeScript · Tailwind · MDX · React 19
Where we work
Fully remote engagements across time zones. We work remote-first, so the time zone matters less than keeping updates clear and regular. We usually collaborate in English.
How we work with Remote worldwide teams
Remote-first engagements run on written updates, a shared backlog, and a weekly demo call. We keep at least four hours of overlap with whichever time zone you work in, and everything else happens asynchronously so nobody waits on a meeting to unblock work.
What Remote worldwide clients usually need
Most remote briefs arrive as a rough product idea with a deadline attached. The first job is separating the slice that has to ship from the rest of the roadmap.
Contracts, data, and compliance
Contracts are milestone-based, invoiced against agreed deliverables. Code lives in your repository from the first commit, so there is no handover cliff if you take the work in-house later.
