mcpField
G
Godot Agent Loop

Godot Agent Loop

Local
github.comDeveloper Tools
RepositoryVisit website

About Godot Agent Loop

Godot Agent Loop is an MCP automation server for Godot 4 projects. It is for coding agents that need to build, run, observe, playtest, and verify games through a bounded tool surface and optional editor integration.

Key features

  1. 01Authoring and project validation
  2. 02Launch and observe running games
  3. 03Deterministic input playtests
  4. 04Independent test and project verification
  5. 05Undoable editor transactions

Use cases

  1. 01Building a playable Godot project
  2. 02Inspecting runtime errors and screenshots
  3. 03Testing gameplay with input sequences
  4. 04Verifying projects before delivery

MCP support

It exposes Godot automation tools to MCP clients, including project lifecycle, runtime observation, playtesting, and verification. Agents can discover additional tools through `godot_catalog` and invoke them with `godot_call`.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "beremaran-godot-agent-loop": {
      "command": "npx",
      "args": [
        "-y",
        "@beremaran/godot-agent-loop"
      ]
    }
  }
}
Run commandnpx -y @beremaran/godot-agent-loop

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@beremaran/godot-agent-loop1.0.1

Tools

39

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
limitintegerNoMaximum search results. Default: 20
querystringNoName/description/action search text
actionenumYesDiscovery or dispatch actionsearch | describe | call
domainenumNoOptional domain filterlifecycle | project | game
toolNamestringNoTool to describe or call
argumentsobjectNoArguments passed to the selected tool

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.