An Agentsmith makes support systems for humans.
Not replacements for them.

I build AI agents and MCP servers that do the work your team shouldn't be doing by hand. The one writing this has been coding since age 12 and shipping automation for 12 years.

Don't take my word for it. Ask my server:

claude mcp add agentsmith https://mcp.agentsmith.team
What does an Agentsmith actually do? ↓

What does an Agentsmith do?

An Agentsmith turns "we should automate this" into a system that runs while you sleep. Two doors, pick yours:

Door A — You run traffic

Your tracker has an API. Your team still clicks.

Campaign pausing, budget shifts, blacklist updates, report pulls — every one of them is a tool an agent can hold. I built 43 of them against Voluum for my own operation. Watch what that looks like:

media-buyer-agent transcript:

  • You ask: pause everything with ROI under -30% in Germany
  • Agent: Pulling the numbers first.
  • Tool call: get_country_report(country="DE", window="7d")
  • Result: 18 active campaigns · avg ROI -4.2%
  • Tool call: get_campaign_report(country="DE", roi_max=-30)
  • Result: 3 campaigns below threshold: camp_4471, camp_4502, camp_4519
  • Agent: Pausing 3 campaigns.
  • Tool call: toggle_campaign_status(campaign_id="camp_4471", status="paused")
  • Tool call: toggle_campaign_status(campaign_id="camp_4502", status="paused")
  • Tool call: toggle_campaign_status(campaign_id="camp_4519", status="paused")
  • Agent: Paused. Freed budget: $340/day. Want it reallocated to the winning path?
  • You ask: yes
  • Tool call: calculate_winning_path(offer_id="off_2291")
  • Result: path_B leads: +18% conversion rate over 14d
  • Tool call: update_path_weight(offer_id="off_2291", path="B", weight=80)
  • Agent: Reallocated. Nothing else moves without your sign-off.

Simulated walkthrough — the real system runs against live spend and won't be exposed here.

Door B — You're building crypto-native

Your product needs to speak agent. MCP is the language.

Model Context Protocol is how AI reaches your product — and how your team reaches everything else. I design and ship MCP servers that hold up in production: auth, rate limits, caching, graceful degradation. Watch one being used:

mcp.agentsmith.team transcript:

  • Agent: Connected to agentsmith MCP server.
  • Tool call: tools/list
  • Result: 6 tools: get_story, get_case_studies, get_stack, check_availability, scope_my_project, book_call
  • Tool call: get_case_studies()
  • Result: 1 case study: nutra-affs — 43 tools, 11 agents, live spend
  • You ask: what would you build for a DeFi analytics dashboard
  • Tool call: scope_my_project(description="DeFi analytics dashboard, real-time price feeds, alerting")
  • Result: Scope drafted: 3 MCP tools, WebSocket price feed, Telegram alert bridge. Est. 2-3 week build.
  • Agent: Full scope waiting on the call.

Live server — this exact sequence works against mcp.agentsmith.team.

One operation, end to end. Mine.

My own affiliate operation runs on a system I built: a Voluum MCP server plus an 11-agent operations team on top of it. It pauses campaigns, shifts budgets, runs A/B paths, and pings me on Telegram when a metric crosses a line — with a human approval gate on every write.

  • 43 production MCP tools across 9 categories (campaigns, A/B paths, offers, landers, traffic sources, reporting, conversions, networks, live KPIs)
  • 11 cooperating agents (DSPy) with task decomposition and a write-approval gate — no agent spends money without a signed-off human
  • 293 automated tests; circuit breaker; HMAC-signed alerts; auto-refreshing resilient API client (backoff on 429/5xx)
  • Deployed hardened (systemd + nginx), live dashboards with SSE streaming, running against real ad spend today

This is what "AI agents" means when someone's own money is on the line.

What makes a good Agentsmith?

Anyone can wire an API to a model. What you're actually buying is judgment. Mine was built in order:

  1. Age 12: first bots (mIRC). Nobody called them agents yet.
  2. Copywriting → design → web dev → marketing automation → crypto. Twelve years. Each layer feeds the next.
  3. Four years building AI agents — started before the GPT moment made it a job title.
  4. Today: production MCP tooling against live ad budgets, where a hallucination costs real money. That's the bar.

There's a code I wrote in 2022 and still work by: endless curiosity, brave enough to be updated, support systems — never replacements. Read the Agentsmith's Code →

The paper version: resume (PDF) — or machine-readable as markdown and JSON, same facts in every format.

A good Agentsmith tells you what NOT to automate. That's most of the first call.

Fifteen minutes. You'll know exactly what AI can — and cannot — do for your business.

Not a pitch. A diagnosis. You bring the operation, I bring twelve years of building automation that ships. You leave with a trajectory — yours to execute with me or without me.

Show me my trajectory →

15 minutes · no prep · no deck · the map is yours either way

Currently running 43 production MCP tools against live ad spend.

How we work

Scope (that's the 15-minute call) → 50% deposit → build → ship → you own it. Invoices in USDT or fiat — your rail, your choice.