chess-coach-mcp

A hybrid AI chess coach exposed as an MCP server. A local Stockfish engine supplies grounded evaluations, mistake classifications and tactical motifs; your MCP host model (e.g. Claude) turns those facts into natural-language — Korean or English — coaching.

The engine knows what the best move is. The model explains why. This project wires the two together and adds the piece neither does alone: "here is your recurring mistake, drilled from your own games."

pip install chess-coach-mcp      # or: uvx chess-coach-mcp   (needs a local Stockfish)

See it in action

<p align="center"> <img src="https://raw.githubusercontent.com/parkseokjune/chess-coach-mcp/main/docs/demo.gif" alt="Demo: a blunder, the engine's preferred move, and the recurring pattern" width="420"> </p>

diagnose_weaknesses turns your recent games into a weakness report — recurring tactical blind spots and where you lose the most (by phase):

<p align="center"> <img src="https://raw.githubusercontent.com/parkseokjune/chess-coach-mcp/main/docs/weakness_report.png" alt="Weakness heatmap: tactical blind spots and average centipawn loss by phase" width="820"> </p>

…then recommend_drills hands back the exact positions you went wrong in — your move in red, the engine's in green — so you re-solve your own mistakes:

<p align="center"> <img src="https://raw.githubusercontent.com/parkseokjune/chess-coach-mcp/main/docs/board_example.png" alt="Annotated drill board: your move in red, the engine's move in green" width="340"> </p>

Numbers above are real Stockfish output; the weakness report uses an example dataset. Regenerate everything with uv run --with matplotlib --with pillow python docs/generate_assets.py.

Why this exists

Engines (Stockfish) tell you the best move but not the reason. Raw LLMs explain fluently but play/evaluate chess poorly and hallucinate lines. Existing trainers are fragmented (one app for stats, one for explanations, one for courses) and rarely give a personalised, guided path. chess-coach-mcp is the grounding layer: every claim the coach makes is backed by Stockfish, and the weakness diagnosis is computed from the player's actual games.

What it does

• Fetch recent games from Lichess or Chess.com (public APIs, no key).
• Analyse a game: per-move classification (best / good / inaccuracy /

mistake / blunder, with Korean labels), win% before/after, centipawn loss, the engine's preferred move, tactical-motif tags, and per-phase summary.

• Analyse a position (FEN): top engine lines in SAN, win%, material, and

fork/pin flags — so the model can explain the why.

• Diagnose weaknesses across many games: phase weaknesses

(opening/middlegame/endgame), recurring tactical blind spots with example positions, leaky openings, a time-trouble proxy, and a ranked top-weakness list.

• Recommend drills: re-solvable positions taken from the player's **own

blunders**, ordered to target their top weaknesses, plus a Lichess daily puzzle warm-up.

What makes it different (차별점)

Most chess tools do one thing well, so you end up stitching several together. chess-coach-mcp is the missing grounding + personalisation layer, delivered right where you already work — inside your AI assistant.

The five things that set it apart:

1. Hybrid & grounded — Stockfish is the judge, the LLM is the explainer.

Every coaching claim is backed by the engine, so there are no hallucinated evaluations or made-up lines (the failure mode of asking a raw LLM about chess).

1. Personal, not generic — diagnose_weaknesses aggregates your games into

phase weaknesses, recurring tactical blind spots and leaky openings; recommend_drills quizzes you on your own blunder positions — not random puzzles at your rating.

1. Bilingual EN/KO — every structured fact carries a Korean label, so the

coaching reads naturally in Korean (한국어 코칭).

1. Local-first & private — your own Stockfish binary + public read-only APIs.

No account, no API key, nothing about your games is uploaded anywhere.

1. Inside your assistant — it's an MCP server, so coaching happens in the same

chat you already use, composable with everything else your assistant can do.

Tools

source is lichess (default) or chesscom. Every numeric/categorical fact ships with a *_ko Korean label for natural Korean coaching. Positions in tool output also carry a board_ascii text board and a lichess_url, so the coach can draw the board right in the chat or link you to an interactive one.

Does a board show up in chat?

This is an MCP server: it returns data (FENs, evaluations, a board_ascii text board, a lichess_url), and your assistant turns that into coaching. So a graphical board doesn't pop up by itself — but the model can print the board_ascii board in any client, you can click the lichess_url for a real interactive board, and on claude.ai the model can draw an SVG board from the FEN. (The demo GIF above is a generated README asset, not the live chat UI.)

Requirements

• Python ≥ 3.11
• Stockfish on your PATH (or set STOCKFISH_PATH):
• macOS: brew install stockfish
• Debian/Ubuntu: apt install stockfish

Install & run

From PyPI:

pip install chess-coach-mcp
chess-coach-mcp               # run the MCP server over stdio
# …or run without installing:
uvx chess-coach-mcp

From source:

uv sync                      # install dependencies
uv run chess-coach-mcp       # run the MCP server over stdio

Register with Claude Code

claude mcp add chess-coach -- uv --directory /ABS/PATH/TO/chess-coach-mcp run chess-coach-mcp

Or add to an MCP client config:

{
  "mcpServers": {
    "chess-coach": {
      "command": "uv",
      "args": ["--directory", "/ABS/PATH/TO/chess-coach-mcp", "run", "chess-coach-mcp"],
      "env": { "STOCKFISH_PATH": "/opt/homebrew/bin/stockfish" }
    }
  }
}

Example coaching flow

"내 리체스 약점 좀 진단해줘. 아이디 myname."

The host calls diagnose_weaknesses("myname"), gets back per-phase ACPL, recurring motifs (e.g. hanging_piece ×4, missed_tactic ×3) with example FENs, then explains in Korean why those positions went wrong and calls recommend_drills("myname") to quiz the user on their own blunders.

Configuration (environment variables)

How move classification works

Moves are classified by the drop in win percentage, not raw centipawns, using Lichess' logistic model — far more meaningful in already-winning or already-losing positions. A move is a blunder if it loses ≥20% win probability, a mistake at ≥10%, an inaccuracy at ≥5%. Mate-aware: a move that throws away a forced mate or walks into one is flagged accordingly.

Tactical motifs are heuristic labels (depth-1 static exchange for hanging pieces, geometric detection for forks/pins/back-rank). They exist to group engine-found mistakes into human themes, not to replace the engine's judgement.

Development

uv run pytest                       # unit + engine tests (skips engine tests if no Stockfish)
uv run python examples/mcp_smoke.py # boot the server over MCP and call tools
uv run python examples/live_check.py <lichess_username>  # live network E2E

Tests marked engine require a Stockfish binary; live tests (none by default) hit the network and are deselected unless you pass -m live.

License

MIT