Service
MCP Server and AI Agent Development for Real Operations
MCP turns an assistant into an operator. I build the servers that expose your systems as tools, and the agents that use them, with the security model that makes it safe: OAuth flows, scoped permissions, consent screens, rate limits and logs.
Examples in production include an MCP-based support agent for a real estate platform and an OAuth shim that lets Claude deploy and inspect services on self-hosted Coolify from a prompt, with sessions persisted and every action auditable.
What you get
Assistants that can read and act on your data through well-defined tools.
OAuth 2.0 protected servers that work with Claude and other MCP clients.
Agents that automate support, operations and deployments with guardrails.
Audit trails and consent so security teams can sign off.
Deliverables
- 01
Tool surface design: what the agent may read, write and never touch
- 02
MCP server implementation (Node/TypeScript or PHP)
- 03
OAuth 2.0 authorization flow, sessions and rate limiting
- 04
Agent loop with tool calling, retries and error handling
- 05
Observability: logs, traces and per-action audit
- 06
Client integration (Claude, internal assistants, chat widgets)
Stack
- MCP
- Claude API
- OAuth 2.0
- Node.js
- Express
- Supabase
- Laravel
- Docker
Where I've done this
- AI · DevOps
Prompt-driven deployments with MCP
An OAuth shim and MCP server that let Claude deploy, restart and inspect services on self-hosted Coolify from a chat prompt.
- Built at SL Tech
REConnect
Real estate MLS data platform serving 100+ brokerages and 20,000+ agents, with AI agents handling about 90% of support tickets.
FAQ
What is an MCP server?
A server that implements the Model Context Protocol, exposing tools, resources and prompts that AI assistants like Claude can discover and call. It is the standard way to connect an assistant to your systems.
Is it safe to let an agent deploy or change data?
It can be, with the right design: narrow tools, explicit consent for destructive actions, scoped OAuth tokens, rate limits and an audit log. I build those controls in from the start rather than bolting them on.
Can you build the agent and the MCP server?
Yes. I've built both sides: servers that expose operations and agents that use them, including the chat surfaces users interact with.