BetterChess
REMOTE · MCP.BETTERCHESS.CO
Chess MCP for Claude: engine analysis, attack maps, game review. One URL, no install.
Available components
Last scanned (20 hours ago)
Scores higher than 99% of remote servers
Reachable. Last reached 4 Nov 2026.
Category Entertainment and Games
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security94
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. View diagnostics → Pass
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
- The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents. View diagnostics → Partial
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability77
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 920 tokens (~230/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 1 Oct 26 +1
- Stability: 0.97 → pass security
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 2 Sept 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “chess_analyse” rewrote its description, which is the text the model reads security
- Schema quality: 205 → 230 ▼ functional
- Stability: unverified → 0.03 ▲ functional
- The server now declares the “prompts” capability functional
- First check of Schema quality: 100 functional
- Schema quality: excellent → good functional
- New prompt “coach” functional
- New tool “chess_rig” functional
- “chess_analyse” added an optional parameter “considering” cosmetic
- “chess_analyse” added an optional parameter “traps” cosmetic
- 1 Sept 26 0
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 4 Nov 2026 · Probed https://mcp.betterchess.co
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=mcp.betterchess.co | CN=YR1,O=Let's Encrypt,C=US | 3 Nov 2026 | 1 Feb 2027 | RSA 2048 | SHA256-RSA | 54f7718d8838504c7ba330288b95b68e578 |
| SANs: mcp.betterchess.co | ||||||
| CN=YR1,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | a20253f15f2691c05dc1ce13b9bcca4e |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of mcp.betterchess.co. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| co. | present | 7786 | 8 | Verified |
| betterchess.co. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Enforced and verified
The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.
| Result | Enforced and verified |
|---|---|
| Enforced | On tool calls |
| HTTP status | 200 |
WWW-Authenticate challenge Bearer resource_metadata="https://betterchess.co/.well-known/oauth-protected-resource"
Bearer resource_metadata="https://betterchess.co/.well-known/oauth-protected-resource"| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000 |
Protected resource metadata
| Document | https://betterchess.co/.well-known/oauth-protected-resource |
|---|---|
| Retrieved | Yes |
| Resource | https://mcp.betterchess.co |
| Authorisation server | https://betterchess.co |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://mcp.betterchess.co | Verified | 200 | |
| http (plaintext) | http://mcp.betterchess.co | HTTPS enforced | 308 | https://mcp.betterchess.co/ |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
chess_analyse Analyse a chess position ~305
Returns an engine evaluation of a chess position: the strongest candidate moves with their scores, and the position's checkable facts — side to move, whether that side is in check, undefended pieces and the pieces attacking them, and the material balance. Accepts a FEN, a PGN, or a list of SAN moves from the starting position. Also reports what the OPPONENT would play if it were their turn, which is the difference between a position being quiet and merely looking quiet. Pass `considering` with a move you are thinking of playing and it returns what that move actually walks into — a losing move is usually not in the top candidates, so asking about it directly is the only way to find out.
| Name | Type | Req | Description |
|---|---|---|---|
| considering | string | – | A move you are thinking of playing, in SAN, e.g. "Ng5". Returns the evaluation after it and the line that refutes it. |
| fen | string | – | FEN of the position. |
| moves | array | – | SAN moves from the start, e.g. ["e4","e5"]. |
| multipv | number | – | How many candidate moves (1-5, default 3). |
| pgn | string | – | PGN; the position after the final move is used. |
| traps | boolean | – | Also scan the captures and checks available to the side to move and return the ones that lose, each with its refutation. Slower — several extra searches. |
No output schema declared.
No examples provided.
chess_attacks What a piece attacks ~140
Returns the exact list of squares attacked by the piece standing on a given square in a chess position, together with that piece's type and colour. Returns an empty list when the square is unoccupied. Accepts a FEN, a PGN, or a list of SAN moves from the starting position.
| Name | Type | Req | Description |
|---|---|---|---|
| fen | string | – | FEN of the position. |
| moves | array | – | SAN moves from the start, e.g. ["e4","e5"]. |
| pgn | string | – | PGN; the position after the final move is used. |
| square | string | yes | The square, e.g. "d5". |
No output schema declared.
No examples provided.
chess_review Review a game for turning points ~189
Replays a finished game ply by ply with the engine and returns the moves where the evaluation swung by more than a threshold (default 1.5 pawns). Each entry gives the move number, the side that moved, the move played, the engine's preferred move, the size of the swing in pawns, the evaluation before and after, and the FEN of the resulting position. Accepts a PGN or a list of SAN moves, and can be filtered to one colour. Long games are truncated at 60 plies.
| Name | Type | Req | Description |
|---|---|---|---|
| colour | string | – | "white" or "black" — whose mistakes to report. Default both. |
| moves | array | – | Or SAN moves from the start. |
| pgn | string | – | The finished game as PGN. |
| threshold | number | – | Swing in pawns that counts as a turning point. Default 1.5. |
No output schema declared.
No examples provided.
chess_rig The live-coach page rig ~118
Returns the JavaScript source of the in-page coaching rig for a chess.com bot game, to be run in that page by the browser's javascript tool. Once running, the page exposes window.__coachWait(ms) (resolves with events and board status), window.__coachWatch.status() (moves, fen, turn, myTurn, result) and window.__coach (beginDraw, play, dashed, label, step, say) for drawing on the board. Also returns the rig version and the URL of the chess.com bot surface.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
How do I install the BetterChess MCP server?
BetterChess is a hosted endpoint at https://mcp.betterchess.co/, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · mcp.betterchess.co
claude mcp add --transport http co-betterchess-betterchess 'https://mcp.betterchess.co/'
What is the BetterChess MCP server?
BetterChess is an MCP server listed in the public MCP registry as co.betterchess/betterchess. Chess MCP for Claude: engine analysis, attack maps, game review. One URL, no install. This page covers its hosted endpoint (https://mcp.betterchess.co).
Is the BetterChess MCP server safe to use?
BetterChess scores 92 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the BetterChess MCP server expose?
BetterChess exposes 4 tools: chess_analyse, chess_attacks, chess_rig, chess_review. Their descriptions and schemas cost roughly 752 tokens of context every time the server is loaded.
Does the BetterChess MCP server require authentication?
Yes. BetterChess asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the BetterChess MCP server still maintained?
BetterChess is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.