Masterclass
AI Customer Use Case

How John Brahy Turns Claude, Everflow's MCP, and AI Agents Into a Real-Time Network Watchtower

John Brahy explains how connecting Everflow's read-only MCP with OpenClaw agent teams, Claude, and self-hosted models flags revenue risk and tracking anomalies in real time, with no agent ever touching a live record.
John Brahy
CTO
@
Ad Trust Marketing
Sign up for expert masterclass content.
Oops! Something went wrong while submitting the form.
Read-Only Security
Learn how read-only MCP keeps live network records safe from rogue AI actions.
Dollar-Ranked Alerts
Discover how background agents prioritize network anomalies strictly by financial risk.
Human-Gated Control
See why every live campaign modification requires explicit human approval before execution.
TABLE OF CONTENTS

Most campaign problems don't show up in a spreadsheet until the damage is already done.

By the time someone stitches three reports together, exports a CSV, and builds a pivot table, a payout has already been cut, a tracking pixel has gone quiet, or a scaling affiliate has moved the budget elsewhere. Reporting lag taxes every delayed decision.

John Brahy got tired of asking his team to babysit dashboards, so he wired Everflow's Model Context Protocol (MCP) server into Claude and a set of autonomous agent teams. The result monitors network health, ranks problems by dollar risk, and surfaces a recommended fix, while every action that could actually change something still needs a human to sign off.

Here's how it's built, where it still needs tuning, and how other operators can run the same playbook.

The Architecture: Evidence, Intelligence, and Control

Everflow's MCP server is read-only by design. Models can query live network metrics, attribution rules, and tracking-domain health, but there's no path to modify a record. That's what makes it safe to point autonomous agents at a live revenue system in the first place.

Brahy keeps knowing and doing on separate rails:

Layer Component Role
Evidence Everflow MCP (read-only) Single source of truth for offers, caps, clicks, conversions, payout rules, and domain health.
Intelligence OpenClaw agent teams Runs recurring baseline comparisons and risk scoring in the background.
Private execution GopherMind (self-hosted models) An internal runtime that lets locally hosted, OpenAI-compatible models query the same MCP endpoints Claude uses. Claude handles the heavy reasoning; GopherMind picks up anything Brahy would rather not send to a third party, so sensitive sub-ID and payout data can get analyzed without leaving his own infrastructure.
Real-time signals Everflow webhooks Event-driven triggers for anything that can't wait on the next polling cycle.
Business context Internal CRM & databases Fuses platform performance with billing, media cost, and rate-card data so the numbers reflect true margin, not just platform-reported revenue.
Enterprise access Claude with MCP connector provisioning Team-wide tool access provisioned centrally instead of everyone authenticating on their own, with usage logged.
Action layer Controlled write path The only place in the system that can change a live record, and only with human approval.

Model execution stays flexible on purpose. Heavy reasoning runs on Claude. GopherMind runs the same MCP queries against self-hosted models whenever the data shouldn't leave internal infrastructure at all.

Ditching the Dashboard: What an "AI Harness" Actually Replaces

Standard network management runs on dashboard fatigue. Answering a routine question means configuring a multi-dimensional report and cross-referencing tabs.

"We'd have to merge a bunch of data together and do a lot of those reports with all the dimensions in the analytics section to get the data that we wanted," Brahy says.

An AI harness sits between Claude and both the Everflow MCP and internal database logs. It picks the right tool for the question, pulls live metrics, and returns a merged answer in chat. No dashboard session required.

"It's just part of my environment," Brahy says. "My AI harness grabs the tools when it needs them. It does it for me."

Dimension Traditional dashboards MCP AI harness
Data extraction Manually configure multi-dimensional reports in the UI. Ask in plain language; tools fetch data in the background.
System switching Bounce between dashboard sessions, bots, and spreadsheets. One workspace combining local logs with live Everflow data.
Time to answer Minutes to hours, depending on the report. Seconds, accessible to any team member without SQL.

On-demand answers save time day to day. The bigger unlock shows up once the same querying runs on a schedule, unattended.

The Always-On Watchtower, and Where It Still Needs a Human

OpenClaw agent teams continuously compare active offer performance against historical baselines across four areas:

  1. Protecting earned revenue. Flagging unauthorized payout cuts, tracking cap pacing, catching expired offers still taking traffic.
  2. Catching silent tracking failures. Clicks continuing while conversions go quiet, isolated through error codes and domain health checks.
  3. Guarding quality and margin. Cross-referencing revenue, payout, and margin to flag high-volume traffic that's actually unprofitable.
  4. Surfacing opportunity. Scanning new Marketplace offers for payout fit and automating month-end CRM and billing reconciliation.

None of this works out of the box. Rolling baselines have to account for real seasonality: a holiday traffic spike or a planned promo push looks identical to an anomaly if the model is only compared against a flat 7-day average.

Brahy's agents weight baselines against known calendar events and wait for a sustained deviation, not a single-interval blip, before something earns a spot in the digest. Skip that tuning step and dollar-ranking just reorders the noise instead of removing it.

The Executive Risk Digest

Findings consolidate into one daily digest, ordered by total dollars at risk. Confirmed losses sit at the top, followed by estimated exposure and technical anomalies. Each line item comes with a severity score, dollar impact estimate, supporting evidence, and a recommended fix. It's a decision packet, not a flag.

Team Distribution and Execution Guardrails

Custom API scripts work fine for a technical founder. Scaling this across a team means provisioning access that doesn't depend on everyone knowing how to write a query. Registering the Everflow MCP centrally gives the whole team the same tool access through Claude, with usage logged per person instead of routed through a shared credential.

Non-technical staff use pre-packaged, multi-step agent skills that run a reporting sequence from a plain-language request. An account manager can pull sub-ID performance or verify a payout history without writing code.

Safety Rails

  1. Least privilege by default. The MCP stays read-only and scoped to the endpoints agents actually need.
  2. Human-in-the-loop authorization. Pausing offers, adjusting caps, or changing routing requires explicit approval through the separate write path.
  3. Decision packets, not raw alerts. Every item includes severity, dollar exposure, evidence, and a proposed action.
  4. Permanent audit trail. Queries and actions are logged centrally, tied to whoever or whatever triggered them.

Compressing the Distance to Decision

The gap between something happening on the network and a human acting on it is where revenue quietly leaks. This setup doesn't close that gap by removing the human. It closes it by making sure the human only has to look at the handful of things that actually matter, with the evidence already assembled. The infrastructure to do this is available off the shelf. The differentiator is in the tuning and the guardrails, not the wiring.

Five Steps to Build Your Own Watchtower

1

Deploy a read-only evidence layer.

Connect Everflow through its MCP server so models can query live data with no write path.

2

Schedule background intelligence.

Run agent loops comparing daily performance against rolling baselines, adjusted for known seasonality.

3

Fuse platform data with internal context.

Connect Everflow metrics to CRM, billing, and rate cards to get to true margin.

4

Order alerts by financial impact.

One daily digest ranked by dollar exposure, not alert count.

5

Enforce human-gated execution.

Keep every campaign modification behind a separate, human-approved action layer with full audit logging.

Subscribe To Our Newsletter
Get tactics and strategy by category that help you grow faster through our fireside chats, webinars, white papers, blogs, and case studies.
I agree to receiving communications.
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.