Chess 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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| new_game_toolA | |
| get_state_toolA | |
| visualize_board_toolA | |
| validate_move_toolA | |
| make_move_toolB | |
| ai_make_move_toolA | |
| undo_move_toolA | |
| evaluate_board_toolA | |
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 8 tools
Each tool clearly targets a distinct operation: game creation, state retrieval, visualization, move validation, move execution, AI move generation, undo, and evaluation. The only potential overlap between make_move and ai_make_move is explicitly differentiated by their descriptions and usage guidance.
Tool names generally follow a verb_noun pattern with a common _tool suffix, making them predictable. Minor deviations include 'new_game' (which is adjective_noun rather than verb_noun) and 'ai_make_move' (which includes a prefix), but these do not significantly harm overall consistency.
With 8 tools, the server is well-scoped for a chess MCP, covering creation, state inspection, moves, AI play, undo, and evaluation. Each tool has a clear purpose, and the count feels appropriate without being bloated or insufficient.
The toolset covers the core chess lifecycle: start a game, view state, validate/make moves (both manual and AI), undo, and evaluate. Minor gaps such as setting AI difficulty or importing arbitrary FEN positions exist, but they are not essential for basic usage and do not cause dead ends.