Minesweeper MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| start_gameB | Start a new game of Minesweeper |
| clickC | Click at a cell on the Minesweeper board |
| flagC | Place a flag at a cell on the Minesweeper board |
| unflagC | Remove the flag at a cell on the Minesweeper board |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: start_game initiates a new game, click uncovers cells, flag marks potential mines, and unflag removes those marks. There is no overlap or ambiguity between these actions, making tool selection straightforward for an agent.
All tool names follow a consistent verb-based pattern (click, flag, start_game, unflag) using snake_case throughout. The naming is simple, predictable, and aligns well with the actions they perform in the Minesweeper domain.
With 4 tools, this server is well-scoped for Minesweeper gameplay. It covers the essential actions needed to play the game (starting, clicking, flagging, and unflagging) without being overly sparse or bloated, making each tool earn its place.
The tool set provides complete coverage for the Minesweeper domain, including game initiation (start_game), core gameplay actions (click, flag, unflag), and no obvious gaps. Agents can perform all necessary operations to play a full game without dead ends.