Service / AI
Make your product callable by every agent.
Model Context Protocol servers that expose your product's data and actions to Claude, ChatGPT, Cursor and other agents, with authentication and least-privilege tools.
[ 01 ]The short answer
What is MCP Server Development?
MCP (Model Context Protocol) is the open standard that lets AI assistants and agents use outside tools and data. An MCP server describes your product's actions and resources so that Claude, ChatGPT, Cursor and agent frameworks can call them. We design the tools agents actually need, add OAuth and per-user scopes, defend against tool poisoning and injection, and publish the server so your product shows up where people now work: inside their AI assistant.
What you get
- MCP server with documented tools
- OAuth integration and scopes
- Security review and threat model
- Deployment and monitoring
- Listing in MCP registries
[ 02 ]What we build
The pieces, built to last.
- 01
Tool design
A small set of task-shaped tools with clear names and schemas, not a dump of every endpoint.
- 02
Remote MCP servers
Hosted servers over streamable HTTP, deployable on Cloudflare, AWS or your own infrastructure.
- 03
OAuth and scopes
Users sign in once and every tool runs with their permissions, never a shared admin key.
- 04
Security hardening
Pinned tool descriptions, input validation, output sanitising and rate limits against tool poisoning and injection.
- 05
Resources and prompts
Read-only resources and prompt templates that help agents use your product well.
- 06
Client testing
Tested against Claude, ChatGPT, Cursor and common agent frameworks before launch.
[ 03 ]Where it pays off
Where it earns its keep.
- 01
SaaS products
Let customers' agents create, update and report on records in your product.
- 02
Internal platforms
Give your staff's assistants safe access to internal data without new dashboards.
- 03
Developer tools
Expose builds, logs and deploys to coding agents in the editor.
- 04
Data providers
Sell access to datasets to agents per request, with metering and keys.
[ 04 ]How we deliver
Four steps, one team, start to finish.
The same people scope it, build it and stay after launch. Timings are typical for a first release; we agree yours after the deep dive.
- 01Week 1
Find the decision
We pick the decision or task worth automating, measure how it is done today and agree what better means in numbers.
- 02Week 1 to 2
Build the eval first
A labelled test set from your own data comes before any prompt or training run, so every change is scored, not argued.
- 03Weeks 2 to 10
Build with guardrails
Models suggest, code decides. Permissions, injection checks, human override and audit logs are part of the first version.
- 04Ongoing
Ship and improve
We launch to real users, watch cost, latency and quality per request, and feed failures back into the eval set.
[ 05 ]Stack
Tools we reach for.
Chosen per project, and we work in yours. Nothing here is a lock-in: you own the code and the accounts.
- MCP TypeScript SDK
- MCP Python SDK
- Cloudflare Workers
- Durable Objects
- OAuth 2.1
- Zod
- Claude
- ChatGPT
- Cursor
[ 06 ]Related work
Built by the same team.
[ 07 ]Further reading
Problems we found, and how we would solve them.
- AI security3 min read
MCP servers are your new supply chain
ProblemAgents trust tool descriptions and outputs from MCP servers they install like packages, so a poisoned description, a compromised server or an over-privileged token can steer or rob them.ProposalPut an MCP gateway between agents and servers: pinned and reviewed tool manifests, per-user scoped tokens, sandboxed local servers, output sanitising, egress allowlists and a full audit log.Read the proposal - AI security3 min read
Prompt injection is an architecture problem
ProblemAny agent that reads untrusted content and can act can be steered by instructions hidden in that content, and no prompt or filter reliably separates data from commands.ProposalAssume injection will happen and limit what it can achieve: keep untrusted content away from privileged decisions, give tools least privilege, put consequential actions behind code-level checks, and break the path to exfiltration.Read the proposal
[ 08 ]FAQ
Questions buyers ask.
The protocol is only as safe as the server. Researchers have catalogued tool poisoning, prompt injection through tool output and malicious packages. We build with pinned manifests, scoped tokens and sandboxing; our article on MCP security is linked below.
Usually the MCP server wraps your existing API. It adds a layer designed for agents, with fewer, task-shaped tools and agent-friendly errors.
Yes, with metered API keys or per-request payments such as x402. See our onchain AI agents service.
[ 09 ]More AI services
- Custom AI Model DevelopmentA model trained on your data, owned by you.
- LLM Fine-Tuning and DistillationFrontier quality at a fraction of the cost.
- AI Agent DevelopmentAgents that finish the job, inside the rules.
- AI Workflow AutomationHours of back-office work, done in minutes.
- RAG DevelopmentAnswers from your documents, with citations.
- AI Memory and Knowledge GraphsAI that remembers what your organisation learned.
- Voice AI AgentsEvery call answered, qualified and logged.
- Document AI and Intelligent Document ProcessingPaperwork turned into clean, checked data.
- Private LLM DeploymentAI on your infrastructure, data never leaves.
- LLMOps, Evaluation and GuardrailsKnow your AI works before customers find out.
- Predictive ML and ForecastingDecisions made on what will happen next.
One company at a time