Skip to content

AI Agents & MCP

The Model Context Protocol is how AI assistants reach real systems instead of guessing. We build MCP servers that expose your data and tools to Claude and other clients, and agents that carry out multi-step work with permissions and audit trails rather than blind trust.

MCP Claude API TypeScript Python Serverless OAuth

What you get out of it

  • Your own data and tools available inside the assistant your team uses
  • Agents that take real actions, with a record of every one
  • Permission boundaries decided by you, not by a prompt
  • An honest read on which steps should stay human

What the work includes

  • MCP servers exposing your systems as tools, resources and prompts
  • Agent workflows with retries, timeouts and failure handling
  • Approval gates on anything destructive or outward-facing
  • Evaluation harness and logging so behaviour is observable

Small business, charity or non-profit?

AI Agents & MCP work is offered at substantially reduced rates. Mention it when you get in touch and the discount is built into your quote.

How it works

Get new articles by email

One email when something new goes up, roughly twice a month. Plain writing on what software costs and what is worth building. No sequences, no sales calls, and one click to leave.

We use it for the newsletter and nothing else. Unsubscribe any time.

Ready to talk about AI agents and MCP?

Send over the details and you will get a straight answer on scope, timeline and cost.

Replies within one business day. Mon to Fri, 9am to 5pm MT.

Call Start a project