What does the server actually do?
It wraps your Ebitengine game so that Cursor can communicate with it through the Model Context Protocol. You only need to call `mcp.Wrap(&Game{})` inside `ebiten.RunGame`.
@sedyh
Basic information
Ebitengine MCP server for Cursor
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Ebitengine Recorder MCP for Cursor is an MCP (Model Context Protocol) server that wraps an Ebitengine game before passing it to ebiten.RunGame, enabling Cursor to interact with the game via the MCP protocol. It is intended for developers building games with Ebitengine who want to use Cursor's AI features with their game context.
Wrap your game with mcp.Wrap(&Game{}) inside ebiten.RunGame. Then add the provided JSON configuration to your MCP servers, specifying the command go run github.com/sedyh/ebitengine-mcp/cmd/trun with arguments ["." , "-mcp"].
go run – no prebuilt binary required.It wraps your Ebitengine game so that Cursor can communicate with it through the Model Context Protocol. You only need to call `mcp.Wrap(&Game{})` inside `ebiten.RunGame`.
Add the JSON configuration to your MCP servers list in Cursor. When Cursor starts the server, it runs `go run github.com/sedyh/ebitengine-mcp/cmd/trun` in your project directory.
You need Go installed, along with the Ebitengine library and the `sedyh/ebitengine-mcp` package. The module will be fetched automatically when you use `go run`.
The README only shows a fixed command with arguments `["." , "-mcp"]`. No other configuration or options are documented.
The README does not mention any authentication or transport security. It uses the default MCP transport (likely stdio, as common for local MCP servers).

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott
Console, Backend and CLI to manage Capgo Instant update and Native build for Capacitor apps Build and upload to app store your mobile app

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP
Comments