Sergio by Serviche
Customer workspaceCampaignsWhy SergioCertificationsFAQBlogLog inRequest access
Log inBook a demoRequest access

For developers and AI builders

Build AI agents for BookingKoala cleaning businesses

Sergio is a customer operations platform for residential cleaning companies, with an MCP server for AI agents.

Give your agent the business's synced booking and customer history (BookingKoala, Launch27, ConvertLabs and others), connected conversations, tasks and procedures, and the tools to act on them with permissions and approval controls.

Build lead follow-ups, VA morning plans and owner reports using the operational data already in Sergio.

Read the quickstartRequest demo access

Docs: Quickstart · Tool reference · ChatGPT and Claude setup

When to use Sergio

Choose Sergio when…Consider another approach when…
You're building for a residential cleaning business.You need a general-purpose backend for unrelated industries.
The business uses Sergio or is willing to onboard.You need access without the business adopting Sergio.
You need customer, booking and conversation context together.You only need a standalone database or a single integration.
Your workflow fits Sergio's exposed actions and approval model.You need actions Sergio doesn't expose. Check the tool reference first.

Skip the integration project

Sergio's MCP lets your agent start with a cleaning business's operational context and available actions already connected. You focus on what your agent should do.

What you'd build from scratchWhat Sergio provides through its MCP
Connect booking, phone and email systemsOne interface to the systems Sergio already connects
Match customers across those systemsA shared customer record with conversation and booking context
Translate raw data into operational decisionsCleaning-specific context: recurring versus one-time clients, upcoming bookings, follow-ups
Give the agent ways to actThe actions Sergio exposes, such as creating tasks or campaigns
Maintain those connectionsSergio handles the underlying integration work

For example, "Find customers overdue for a follow-up and prepare the next step" becomes an agent workflow instead of an integration project.

Why build on Sergio

Skip the plumbing

Clients, leads, cleaners, tasks, tags and lists are already modeled and connected. You start on the part that makes your product different.

Booking data, synced every night

No reverse engineering or brittle syncs of your own. Sergio pulls BookingKoala every night and reads its notification emails as they arrive; Launch27 and ConvertLabs sync nightly, read-only. Customer and job history is already in Sergio, ready to read and query.

Task management that runs on its own

Sergio creates and tracks tasks from what happens in the business, and clears them when the work is done. Your agent plugs into it instead of rebuilding to-dos and reminders.

Campaigns and review follow ups built in

Automated texts, emails and review requests already work, so you don't have to rebuild outbound.

Works with the AI you already use

Any client supporting remote MCP over Streamable HTTP, including Claude, ChatGPT, Cursor, Muse, Grok and custom agents. OAuth for AI clients, an agent key for scripts.

Shaped by real operators

Built inside cleaning companies running it every day, so the edge cases come from real days, not guesses.

What your agent gets

Customers

Contacts, history, notes, tags and lists. Search, read and edit.

Schedule

Upcoming and past bookings with the customer and the team assigned. Read only.

Messages

Texts, emails and calls in one thread per customer. Draft replies for review.

Team

Staff, their weekly hours, time off and scheduling rules. Read and update.

Campaigns

Build a campaign, choose its audience, write its messages and read the results.

Tasks

Create, assign, snooze and complete the team's work.

Handbook and training

The company's own procedures, plus training modules and quiz questions you can write and assign.

Events

A cursor feed of new texts, emails, calls and booking changes. Poll it, then acknowledge what you handled. At least once; kept 7 days.

  • Every tool is listed with its inputs in the tool reference, marked read-only or change.
  • Every tool that changes the business takes an idempotency_key. A retry with the same key returns the original result instead of acting twice; the same key with different inputs is refused.
  • Limits: 60 requests a minute and 4 at once per key, 180 a minute and 8 at once per business. Over a limit you get HTTP 429 with Retry-After.

How you connect it for a client

  1. Your client's business uses Sergio. If it doesn't yet, they request access and their customer history is imported.
  2. Add the MCP server https://sergio.serviche.com/api/agent/mcp to your agent or AI client. It is a remote server over Streamable HTTP, listed in the official MCP Registry as com.serviche/sergio.
  3. Your agent signs in one of two ways. AI clients like Claude and ChatGPT open Sergio sign-in through OAuth and the owner or an admin approves it. A custom agent uses an agent key the owner or an admin creates under Add agent; it is shown once, so store it as a secret. Either way your agent gets its own seat on the team.
  4. The seat's role (admin, manager or member) sets what it can read and change, following the business's own access rules. The owner can narrow it, pause it or remove it in Sergio at any time.
  5. One seat covers one business. Each client business approves your agent separately, and a token never reaches another business.
  6. Start with reads. The quickstart walks through a first call.

Owner-controlled sending and approvals

The worry that stops most owners from saying yes to an AI build is a text nobody meant to send. Sergio gives the owner the controls, so it's a feature you can sell.

  1. Drafts never send. create_draft writes a reply that waits in Sergio for the team to review.
  2. Sends take two steps. A first call to a send tool returns the exact text, the recipient and a confirm token, and sends nothing. Only a second call with that token sends.
  3. The owner controls Sending. The owner can switch Sending off for the business, which holds every send. Only the owner raises it, inside Sergio, by retyping their name; no agent can change it.
  4. Opt-outs and quiet hours always apply. A held send comes back with held: true and the reason, never silently dropped.
  5. Everything is logged. Each tool call is recorded against your agent's seat with what it changed, so the owner can see who did what.

What builders make with it

Lead follow-up

Watch the events feed for new inquiries, read the customer's history, and draft the first reply and the follow-ups in the business's voice from its handbook. The office reviews and sends.

Owner reports

A weekly read on new leads and how fast each got a reply, cancellations and their reasons, and what each campaign brought in, written in plain language.

VA morning plan

Each morning, read the day's schedule, open conversations and overdue tasks, and give the virtual assistant a short ordered plan as tasks in Sergio.

Training from the handbook

Turn the company's procedures into training modules and quiz questions, and assign them to new hires.

Who it's for

  1. AI builders shipping vertical tools for home services
  2. Agencies building automations for cleaning company clients
  3. Operators who want their own custom agent on top of their business data

Free to build and test. Included when your client subscribes.

  1. Building and testing: free on TidyHome, our demo business with made-up customers. Access is by invitation for now: request demo access.
  2. A real business: MCP access is included in the business's Sergio subscription. There is no separate connection or agent-seat fee. AI use beyond what the plan includes is billed separately.
  3. Several clients: each business has its own Sergio subscription and approves your agent separately. Either the business or your agency can pay.
  4. High-volume or embedded products: talk to us about a custom agreement.

Questions builders ask

What is the Sergio MCP?

A remote MCP server that gives an AI agent a residential cleaning company's customers, bookings, conversations, team, tasks, campaigns and handbook, plus the actions Sergio exposes. The server address is https://sergio.serviche.com/api/agent/mcp and it is listed in the official MCP Registry as com.serviche/sergio.

Which AI clients can connect to it?

Any client that supports remote MCP servers over Streamable HTTP, including Claude, ChatGPT, Cursor, Muse, Grok and custom agents.

How does my agent get access to a client's business?

Two ways. An AI client like Claude or ChatGPT signs in through OAuth, and the business owner or an admin approves it in Sergio. A custom agent uses an agent key that the owner or an admin creates under Add agent; Sergio shows it once, so store it as a secret. Either way your agent gets its own seat on the team with a role that sets what it can read and change, and the owner can revoke a key, pause the seat or remove it at any time.

Which business systems does Sergio already connect?

Booking platforms like BookingKoala, Launch27, ConvertLabs and others for bookings and customer history, the business's phone line for texts and calls, and email. Your agent reads them through one interface instead of one integration each.

Can my agent send texts or emails to customers?

Drafts never send. A send takes two calls: the first returns the exact text, recipient and a confirm token and sends nothing; the second, with the token, sends. The business owner can switch Sending off, which holds every send, and opt-outs and quiet hours always apply.

How fresh is the booking data?

Sergio pulls BookingKoala every night (between 1 and 4 AM local time) and reads its notification emails as they arrive. Launch27 and ConvertLabs sync nightly and read-only. Texts, emails and calls on the business line arrive as they happen.

How does my agent hear about new messages?

Through a cursor feed, not a webhook: subscribe once, poll events_list, fetch details with read, then events_ack. Delivery is at least once, so dedupe on event_id. Events are kept 7 days.

What does it cost?

Building and testing on our TidyHome demo business is free. A real business needs a Sergio subscription, which includes MCP access with no separate agent-seat fee; AI use beyond what the plan includes is billed separately. Each client business has its own subscription.

Can I try it before I have a client on Sergio?

Yes. We connect your agent to TidyHome, our demo cleaning business with thousands of made-up customers, so you can build against real-shaped data with no real people in it. Access is by invitation for now.

Try it on our demo business

Connect the Sergio MCP and try it on our demo business, TidyHome. Tell us what you're building and we'll give your agent a seat. Building for several clients? Say so; we're working out how we partner with builders.

Request demo accessBook a walkthrough
sergio

Customer operations software for residential cleaning companies.

Product

Customer workspaceCampaignsWhy SergioCertificationsSergio MCPFor buildersFAQ

Works with

BookingKoalaConvertLabsLaunch27QuoGmail

Company

Log inBook a demoContactReferral partnersBlogServicheShowcasePrivacyTerms
© 2026 Serviche. Sergio is customer operations software for residential cleaning companies.
G2 Reviews on G2P Product Hunt