Building Custom MCP Tools on Sentrum Developer Tier.

Pro tier gives you the five default MCP tools (campaign diagnostics, creative analysis, account context, recommendations, askQuestion). For most people that's the whole workflow. But once you've been using Sentrum from Claude Code or Cursor for a few weeks, patterns emerge that the defaults don't cover.

Developer tier solves that. You define your own tools, register them with Sentrum's MCP server, and your AI agent can call them like any other tool — same auth, same workspace scoping, same Sentrum account context underneath.

What a custom tool looks like

A tool is three things: a name, an input schema, and a server-side handler that returns JSON. Example: an agency that wants a "client-ready Slack message" tool that pulls the week's diagnosis and formats it in their voice:

// Define the tool in your Sentrum workspace's MCP registry
{
  "name": "sentrum.draftClientSlackUpdate",
  "description": "Drafts a 4-sentence Slack update for the agency
    client in our house voice. Always opens with the headline number,
    closes with the next action. No jargon, no 'the algorithm'.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "clientWorkspaceSlug": { "type": "string" },
      "dateRange": { "type": "string", "enum": ["7d", "14d"] }
    },
    "required": ["clientWorkspaceSlug"]
  }
}

The handler runs server-side. It can call any of Sentrum's internal endpoints, your own database, or external APIs you've authorized. The MCP client sees one tool call; under the hood it can fan out to whatever you need.

Three patterns we see at launch

Pattern 1 — House-voice client reports

Agencies have a voice. Default LLM output doesn't. Wrap your tone, your closing CTA, your "always include profit-ROAS" rule into a custom tool. Your agent reaches for it when you ask for a client update, the output ships in your voice every time.

Pattern 2 — Custom scoring

Sentrum's default diagnostics use a generic-but-good scoring system. If you've developed your own scoring — say, a creative-fatigue index weighted by your specific funnel data — you can expose it as a tool. The agent calls myCo.creativeFatigueIndex and gets your score back, not the default.

Pattern 3 — Cross-source merges

The Meta API knows Meta. Sentrum knows Meta + your account context. But neither knows your CRM. Wrap a tool that joins Sentrum data with your customer LTV table, and the agent can answer "which creative drove highest-LTV customers" — a question neither system can answer alone.

Webhook subscriptions

Custom tools are pull-style — your agent has to ask. Webhooks are push-style — Sentrum tells you when something happens. Available subscriptions:

• anomaly.detected — fires when Sentrum detects a material KPI move
• recommendation.created — fires when a new action recommendation is generated
• insight.generated — fires when a daily pulse or Blueprint completes
• pattern.observed — fires when Sentrum's account-memory layer learns a new pattern

Each fires a signed POST to your endpoint with a typed payload. Wire to Discord, Slack, your ops dashboard, or directly into another MCP tool to trigger downstream automation.

2,000 calls per day, not per month

Pro tier caps you at 200 AI calls / month. That's fine for dashboard-driven use — 6-7 diagnoses per day, plenty. Once you're running an agent loop that hits Sentrum throughout the day, that cap melts in an afternoon.

Developer is a daily-cap tier: 2,000 calls/day, every day. Functionally unlimited for the workflow we see at this tier (agent loops, monitoring, multi-account dashboards). Hard cap exists to catch runaway scripts and key leaks.

What's included from Pro

Everything. Developer is additive — full Sentrum AI engine (multi-pass diagnostics, account memory, anomaly detection, creative analysis), white-label PDF + Excel exports, team seats, MCP server access, all five default MCP tools. Then layer the Developer features on top.

Who this is not for

If you're using Sentrum from the dashboard, you don't need Developer. Pro covers everything. Developer is for the workflow shift — when you're running media buying through an AI agent more than through the dashboard, and you need the agent to do more than read.

Most users start on Pro, upgrade to Developer once they've built a few prompt patterns that they want to wrap into tools.