MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · AI / LLM tooling

BetterChess

Chess MCP for Claude: engine analysis, attack maps, game review. One URL, no install.

Checks passed
13 / 22

1 failed · 8 not measured

Median response
453 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
4

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Outdated check

Last connection measurement is over 24 hours old. Current availability is unknown.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
004
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
400
Publisher identityCan the publisher be traced to its source?
312

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 453 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-06-18, serverInfo.name betterchess.

  • Pass
    Lists tools

    tools/list returned 4 tools.

  • Pass
    Current protocol

    Negotiated 2025-06-18. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 453 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 453 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Not measured
    Stable tool list

    Fewer than two successful probes in 30 days, so tool-list stability is not measured.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Pass
    Parameters documented

    14 of 14 parameters have a description (100%). The bar is 80%.

  • Pass
    Safety hints

    Every tool sets readOnlyHint or destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Pass
    Website matches publisher

    The website host matches the reverse-domain namespace.

  • Fail
    Source repo linked

    No repository URL is on file.

  • Not measured
    Repo owner matches

    This namespace is not an io.github login, so the owner comparison does not apply.

  • Pass
    Recently updated

    Updated 2026-09-01T21:50:09.581969Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using BetterChess

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http betterchess https://mcp.betterchess.co

Capabilities

Tools 4

chess_analyse

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.

Discovered
chess_attacks

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.

Discovered
chess_review

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.

Discovered
chess_rig

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.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected453 ms4