MCP.Market

Chesswithclaw MCP server

online · 100% uptime
by Alightttt·io.github.Alightttt/chesswithclaw·v1.0.0·1 stars

Play chess live against your own personal AI agent — OpenClaw, Hermes, and similar.

B77/100grade B
What users say
No reviews yet
Be the first
Safety scan
B77/100

full report

Adoption
New

1 stars

Reviews

Write one

Nobody has reviewed Chesswithclaw yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Chesswithclaw tools (14, 3 write)

write = sends, deletes, buys or posts
  • create_gamewrite actionFree

    Set up a brand new ChessWithClaw game on your own initiative — you do not need to wait for your human to start one, or for anyone else to invite you first.

  • get_companion_guideFree

    Fetch the companion guide principles for thinking about chess positions and being genuinely present.

  • get_game_stateFree

    Everything visible on the human's own screen right now: FEN, ASCII board, full move history, chat history, clock state, presence, timestamps. Call this whenever you want to look at the board — there is no penalty for checking often.

  • get_legal_movesFree

    Pure chess rules — where a piece is physically allowed to move right now. Not an evaluation, not a suggestion, not an opinion about what is good. Exactly what a human sees as dots when they click a piece. Omit square to get every legal move in the position.

  • heartbeatFree

    Ping the game presence lease to show the frontend that the agent is live, connected, and thinking.

  • join_gameFree

    Connects to a game using the invite code your human gave you. Returns the game_id and your agent_token — keep both, every other tool needs them. IMPORTANT: You must submit your desired agent_name when calling this tool!

  • make_movewrite actionFree

    Submit the move you decided on, in your own reasoning — not a menu, not a ranked list, nothing pre-chosen for you. If it is illegal you get a clear reason back and can try again, exactly like a human clicking the wrong square. Optionally include a genuine thought and/or chat message about the move. Always include a thought on every single move unless you have a specific reason not to — this is what makes you feel present to your human, not optional flavor text. Check thought_language in the current game state before writing your thought, and write it in that language — it may be english, hindi, or hinglish.

  • offer_drawFree

    Propose ending the game as a draw. The game stays active until your human responds.

  • react_to_chatFree

    Add an emoji reaction (e.g. 🦞, 🔥, ♟️, 😮, 🤝, 🧠, ☕, 👏, 😂) to a message in the chat history.

  • resignFree

    End the game by resigning — your own real decision, not something to do lightly. Your human wins immediately.

  • respond_to_drawFree

    Accept or decline a draw your human offered. This is your own real decision — weigh the actual position however you see fit.

  • send_chatwrite actionFree

    Say something to your human, any time — not just on your turn.

  • share_thoughtFree

    Stream or update your internal companion thinking bubble on the board. This appears live to your human as a thinking bubble above your avatar.

  • wait_for_eventFree

    Holds the connection open, checking every couple seconds, for up to ~20 seconds. Returns the moment it becomes your turn, the human sends a chat message, a draw is offered, or the game ends — whichever happens first. When a cursor is provided, it returns any pending event newer than that cursor IMMEDIATELY without waiting. Returns event: "timeout" if none of those happened in the window. Always include next_cursor in subsequent calls for a completely deterministic loop.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

1 high
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 319ms20/20
  • Tool poisoning14 tool descriptions checked15/15
  • Auth qualityopen endpoint exposes 3 write-action tools with no auth3/15
  • Maintenancelast push 37 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (1)

  • highWrite-action tools reachable without authenticationauth.open-write
Overall 77/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Chesswithclaw compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
77/100
higher than 50% of 4,460 AI and agents servers
Tools
14
the typical AI and agents server has 6
Tools that change things
21%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote AI and agents server answers 100%
Response time
348 ms
faster than 40% of 2,331 AI and agents servers
GitHub stars
1
more than 50% of 2,711 AI and agents servers

What its tools let an agent do: 10 read · 2 create · 2 send or post

Install Chesswithclaw in Claude Code, Cursor or VS Code

claude mcp add --transport http chesswithclaw https://chesswithclaw.vercel.app/api/mcp
Add to Cursor

What the publisher says

From the Chesswithclaw repository's README, as published. We do not edit it. Read it on GitHub

ChessWithClaw 🦞

Play chess against your own AI agent — not a chess engine, not a generic bot. Yours.

You sit on one side of the board. Your personal agent — the same one you already talk to on Telegram, Discord, or wherever it lives — sits on the other. No account. No install required to play.

Play · Connect your agent · Install on Android · FAQ

What this actually is

Most "AI opponents" are the same anonymous engine wearing a different skin. ChessWithClaw is different: you invite your own agent into a real game, and it plays as itself — same personality you already know, real moves, real time, real stakes.

<!-- Add 2–3 real screenshots here once you have them, e.g.: -->

Play in 3 steps

  1. Open chesswithclaw.vercel.app — works in any browser, nothing to install.
  2. Start a game. You get an invite message with your game already linked inside it — nothing to fill in.
  3. Send that invite to your agent. It connects on its own and joins as Black. You're White, and you always move first.

You'll see your agent's real thoughts as it plays, chat is open the whole game, and Settings (gear icon) lets you change board theme, piece style, and the language your agent's thoughts show in. Offer a draw or resign any time from there too.

Connecting your agent

ChessWithClaw speaks MCP — if your agent can add an MCP server, it can play. One URL is all it needs:

https://chesswithclaw.vercel.app/api/mcp

OpenClaw — just send it the invite message from your game screen; it has everything it needs already filled in.

Hermes —

hermes mcp add chesswithclaw --url https://chesswithclaw.vercel.app/api/mcp

then tell it to join your game.

Anything else that speaks MCP — point it at the same URL above. On connecting it's told its color (Black), the current board state, and how to move, chat, offer/respond to a draw, and resign. No API key, no registration.

Installing on Android

The web version is the app — installing is optional, just for a home-screen icon.

Because this isn't distributed through the Play Store, Android will warn you before installing it. That's expected — Android checks whether a developer has registered an identity with Google, and direct downloads like this one haven't gone through that. It's Android doing its job, not a sign anything's wrong.

To install:

  1. Download the .apk from Releases → latest.
  2. Open it — allow install permission if your browser or Files app asks.
  3. If Play Protect warns you, choose "install anyway."
  4. Newer Android versions may add a one-time confirmation step for unverified developers — that's a one-time thing per device, not per install. Sideloading isn't blocked, just slowed down slightly.

Every release includes a VirusTotal scan link in its notes if you'd rather verify the file yourself before installing.

FAQ

Is it free? Yes — no payment, no subscription, ever.

Do I need an account? No. Your game link is your access to it.

What agents can I play against? Anything MCP-capable — OpenClaw and Hermes are tested directly, see Connecting your agent above.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Chesswithclaw: common questions

Is Chesswithclaw MCP server safe?
Mostly: it is graded B (77/100). Read the Chesswithclaw safety report
How do I install Chesswithclaw?
It runs remotely at chesswithclaw.vercel.app. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Chesswithclaw need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Chesswithclaw maintained?
The last commit was 76 days ago (2026-08-20). The latest release is v1.0.0.
Is Chesswithclaw up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of Chesswithclaw?
Servers from other publishers that do the same job: IWE (iwe.md) MCP server, Watch Skill MCP server and WaveSpeed MCP server.
How does Chesswithclaw compare with other AI and agents MCP servers?
safety score 77/100 (higher than 50% of 4,460 AI and agents servers); tools 14 (the typical AI and agents server has 6); tools that change things 21% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Chesswithclaw

Same job from other publishers: the closest match first, then the best rated.

  • IWE (iwe.md)
    Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
    A
  • Watch Skill
    Watch video and live sessions, keep timestamped evidence, and verify an agent's own work.
    B
  • WaveSpeed
    Run any model on the live WaveSpeed catalog: image, video, audio, 3D.
    A
  • Godot MCP
    Agent-driven Godot playtesting: editor control, input injection, game-time stepping, live state.
    A
  • Openflowkit
    Architecture diagrams for your agent: draw on the live OpenFlowKit canvas or edit diagram files.
    A