Skip to main content
Data & Schema

Not translated yet — showing English.

Backoffice MCP Integration

MCP lets an AI agent work in your project the way you do in the Backoffice. Connect an agent such as Claude or Cursor, and it can read your data, evolve your schema, manage players and the catalog, and deploy functions, by chatting in plain language. Everything is on AI Access under Engineering in the sidebar.

Model Context Protocol is an open standard for giving AI agents tools. PlayServ's MCP server offers the agent the same operations as the Backoffice, with the same permissions as the person who signs in.


What the agent can do

AreaFor example
From brief to backendStand up a whole project from a single brief: schema, catalog and functions.
Schema & migrationsAdd fields, create entities, plan and apply safe migrations.
DataQuery, create and bulk-import records; manage relations and saved views. Records of a player-owned entity can't be created by the agent: they need a signed-in player.
PlayersLook players up, manage sessions, suspend or ban.
Catalog & storefrontsManage items and integrations, publish storefronts.
FunctionsInspect and deploy functions, manage secrets, read metrics and logs.
AnalyticsPull dashboards, baselines and events.
Projects & keysCreate projects, issue and rotate API keys.

Built-in recipes walk the agent through multi-step jobs, such as setting up a project from scratch. The agent can also reach a few things the Backoffice doesn't show, like raw fields and pushing a schema from code.


Permission tiers

Every tool is Read, Write or Admin, so you can let reads run on their own and confirm the rest.

TierWhat it doesSuggested approvalEndpoint
ReadLists, gets, queries, dashboards, metrics, logs. No changes.Auto-approve/mcp/read
WriteCreates, updates, publishes, enables. Reversible changes.Ask each time/mcp/write
AdminDeletes, key and session revocation, player bans, disconnects. Destructive.Deny by default; approve each call/mcp/admin

Your MCP client groups the tools by tier on its own when you connect to /mcp. To handle the tiers separately, add each endpoint as its own server and set approval per server in the client.


Connect your client

Add the server to your client

Open AI Access → Connect MCP and copy the configuration into your client: Claude Desktop, Claude Code, Cursor or any other MCP client.

{
  "mcpServers": {
    "playserv": { "type": "http", "url": "https://platform.playserv.com/mcp" }
  }
}

In claude.ai, add it as a custom connector instead: under Settings → Connectors (or Organization settings → Connectors on a Team or Enterprise plan), choose Add custom connector, name it PlayServ and paste the URL.

Sign in

The agent's first PlayServ tool call opens a sign-in page. Sign in with the Google or GitHub account that has access to your PlayServ studio. The agent then acts with that account's permissions.

Check the connection

Ask the agent "What PlayServ tools do you have?". It should list them. To inspect the server without an agent, point the MCP Inspector at the same URL.

Never give the agent an API key

The agent signs in as you; it doesn't need your project's API keys, and a key pasted into a chat may be stored with the conversation. Keep keys in your game, servers and CI.


Pick a project

Tell the agent which project to work in by its slug, which is in the project's settings on Projects. The agent finds the project and uses it for the rest of the conversation.


Change the schema safely

Ask for changes in plain language; the agent describes what it is about to do before doing it. Review its plan before you confirm.

U
List all entities in this project and describe what each one is for.
AI
The project has 4 entities:
  • Ships — the ships players can fly
  • Pilots — one per player, player-owned
  • MatchResults — a result per pilot per match
  • ArenaConfig — singleton with the match rules
Want me to list the fields of any of them?
U
Add a boolean field IsRetired to Ships. It should be required and default to false.
AI
I'll stage this change to Ships:
  • Name: IsRetired
  • Kind: Primitive — Boolean
  • Required: yes, Default: false
Ships has records, so this goes through a migration: existing ships get the default. Shall I plan it?
U
Create an enum called Difficulty with values Easy, Normal, Hard and Extreme.
AI
Created enum Difficulty with 4 values: Easy, Normal, Hard, Extreme. It can now be used by Enum reference fields.
U
Which objects reference or include the Weapon part?
AI
Weapon is used in 2 places, both in the Loadout part:
  • Inclusion field Primary, 1-to-1
  • Inclusion field Secondary, 1-to-1
Loadout itself is included in Pilots.
U
Ships has three fields about handling. Move them into a new part called Handling and include it in Ships.
AI
Here's the plan:
  • Create part Handling with the three fields
  • Add inclusion field Handling on Ships, 1-to-1
  • Remove the three fields from Ships
Removing fields from an entity with records is a migration; I'll show you its impact before applying. Proceed?

Small changes the agent can make directly, like a new object or an optional field, take effect at once. A change that would break existing records, such as removing a field or making one required on an entity that has records, is refused as a direct change: the agent plans it as a migration, shows you its impact, and applies it when you agree. Access settings changed by the agent apply at once, without the migration the Backoffice stages them in.


Generate a schema from a game design document

Paste a game design document, or any description of your game's data, and ask the agent to build the schema from it. It reads the document, proposes the entities, parts and enums, and creates them once you approve.

Ask for the plan first

Before anything is created, ask the agent to summarise what it found and what it will create. Then check the result in Schema before you build data on it: renaming or removing fields once records exist takes a migration.


Next steps

Last updated on 16 Oct 2026