Model Context Protocol specialists
Newer tools change quickly, so it helps to work with someone who has already shipped the pattern you are buying.
We document the prompts, tools, schemas, and day-to-day runbooks so your team can run the system after we hand it over.
We work best with teams adopting agentic AI tooling who want a partner that ships. 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. Nothing here waits on a handover between separate teams.
- 02
Design
System design, AI/tool boundaries, interface direction, and interaction prototypes. On MCP development projects we favour practical architecture over trendy defaults.
- 03
Build
Modern stack, clean architecture, evaluated AI behavior, and iterative demos you can react to. The work for teams in New York stays tied to the outcome you asked for.
- 04
Launch
Ship, monitor, harden, and keep improving models, tools, and product after go-live. You see progress on the critical path every week.
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.
A local agency in New York
Same timezone and a face to meet, which genuinely matters for some teams. You are also paying New York companies hiring on portfolio proof and production AI. rates for the whole team including the layers that never touch your MCP development, and a local shortlist is a small shortlist.
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
Brain Blog
Frontend · Gatsby · Strapi
Custom Gatsby blog with Strapi CMS, built for fast content publishing and a clean reading experience.
Freelance content product pairing Gatsby performance with Tailwind styling and a Strapi-powered editorial workflow.
- · Gatsby static generation
- · Strapi blog integration
- · Tailwind-driven layout
- · Fast content browsing
Gatsby · Tailwind · Strapi
Dumbiez
Frontend · NFT product
NFT comics platform for exploring and interacting with digital comic collectibles.
Independent Next.js product for browsing and engaging with NFT comics, styled with Tailwind and shipped on Vercel.
- · NFT comics browsing
- · Interactive collectible UX
- · Responsive Next.js UI
- · Vercel deployment
Next.js · React · Tailwind · Vercel
Working with teams in New York
New York companies hiring on portfolio proof and production AI. We work with clients in New York remotely and keep overlapping hours in EST/EDT. We usually collaborate in English.
How we work with New York teams
New York is on ET, so our afternoon covers your morning. In practice that means a scheduled daily window for anything that needs a conversation, and written updates waiting when you start.
What New York clients usually need
New York briefs cluster around fintech, media, and B2B SaaS. A lot of the work is replacing a prototype that got a company to revenue but cannot carry the next stage of growth.
Contracts, data, and compliance
Contracts are usually US contractor agreements with IP assignment and an NDA. Fintech projects get SOC 2 evidence and audit logging scoped into the build rather than retrofitted before a raise.
