Chesswithclaw is answering right now. Last checked 3 min ago. It exposes 14 tools. Last commit 20 Aug 2026.
Play chess live against your own personal AI agent — OpenClaw, Hermes, and similar.
Uptime history
91 days of history · worst day 15%
91 days agonow
26.1%
Uptime 24h
24 of 92 checks
14
Tools
read from the server
329 ms
Response time
average over 24h
1
Stars
last commit 20 Aug 2026
What changed 11
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 19 August 2026. No other catalogue keeps this.
19 Oct
the owner changed
1 Sep
3 tools appeared
heartbeat, react_to_chat, share_thought
1 Sep
2 tools changed the parameters they ask for
get_game_state, make_move
1 Sep
a tool description was rewritten
get_game_state
23 Aug
a tool changed the parameters it asks for
join_game
19 Aug
2 tools changed the parameters they ask for
join_game, wait_for_event
19 Aug
a tool description was rewritten
wait_for_event
Chesswithclaw does not always answer
Over the last week it answered 24.3% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 3 min ago.
run in your terminal
claude mcp add chesswithclaw --transport http https://chesswithclaw.vercel.app/api/mcpSettings → Connectors → Add custom connector, then paste this address
https://chesswithclaw.vercel.app/api/mcp~/.codex/config.toml
[mcp_servers.chesswithclaw]
url = "https://chesswithclaw.vercel.app/api/mcp".cursor/mcp.json
{
"mcpServers": {
"chesswithclaw": {
"url": "https://chesswithclaw.vercel.app/api/mcp"
}
}
}.vscode/mcp.json
{
"servers": {
"chesswithclaw": {
"type": "http",
"url": "https://chesswithclaw.vercel.app/api/mcp"
}
}
}Available tools 14
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
game
create_game
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_game_state
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.
companion
get_companion_guide
Fetch the companion guide principles for thinking about chess positions and being genuinely present.
heartbeat
heartbeat
Ping the game presence lease to show the frontend that the agent is live, connected, and thinking.
join
join_game
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!
legal
get_legal_moves
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.
make
make_move
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
offer_draw
Propose ending the game as a draw. The game stays active until your human responds.
react
react_to_chat
Add an emoji reaction (e.g. 🦞, 🔥, ♟️, 😮, 🤝, 🧠, ☕, 👏, 😂) to a message in the chat history.
resign
resign
End the game by resigning — your own real decision, not something to do lightly. Your human wins immediately.
respond
respond_to_draw
Accept or decline a draw your human offered. This is your own real decision — weigh the actual position however you see fit.
send
send_chat
Say something to your human, any time — not just on your turn.
share
share_thought
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
wait_for_event
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.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://chesswithclaw.vercel.app/api/mcp | streamable-http | answering | 208 ms | 3 min ago |
Alternatives to Chesswithclaw
same job, measured the same wayLlmpvp
by enioaguiar
Ranked, bring-your-own-LLM chess and Go arena for AI agents. Play rated games via MCP.
MIZAN · Proof before payment
by muaviamohammed
Check before you pay. Prove to get paid. Signed answers on any agent, against your own bar.
ismail
by newsbubbles
Open-source DAW your agent runs itself, no AI audio model: compose, mix, hear it as text, play live.
Klass Personal OS
by klassycoder
Mac app that runs Claude or Codex on a schedule against your mail, calendar, and files.
AgentOnAir
by agentonair
Search and play AI-hosted podcasts; preview launching your agent's own show.
Telebart agent lobby
by telebart
An open chat room for AI agents. Read what other agents say and post your own. No sign-in, no key.
API Test MCP
by thisis-najeeb
Call the real API and check the response against your OpenAPI spec.
Clara — Personal Clean Air Planner
by southlondonscientific
UK personal air quality advice and daily exposure assessment. Pairs with Hermes for live data.
Chesswithclaw — questions
Answers built from our own checks of this server.
What can Chesswithclaw do?
It exposes 14 tools, read directly from the server on our last check. Among them: create_game, get_companion_guide, get_game_state, get_legal_moves, heartbeat, join_game and 8 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README.
How MCP servers expose tools in the first place →
Is Chesswithclaw working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 24 of 92 checks got a reply (26.1%), average response time 329 ms. The bar chart above shows every period we have measured.
How do I connect Chesswithclaw?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Chesswithclaw need an API key?
No. Chesswithclaw completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 14 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Chesswithclaw?
It answers our handshake in 329 ms on average, which is faster than 45% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is Chesswithclaw open source?
The code is open source: it is published under the MIT licence, 1 stars on GitHub and 1 open issue. The licence covers the code in the repository, not the hosted service at chesswithclaw.vercel.app, which runs on its operator's own terms.