ZBS Index What actually exists in applied AI, with the source next to it

mcp server

chesswithclaw

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

Description as published by the maintainer. Source

  • version 1.0.0
  • active

active — Most recent push to the repository was 2026-08-05.

What this server can do

11 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

create_game(agent_name)
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_guide
Fetch the companion guide principles for thinking about chess positions and being genuinely present.
get_game_state(game_id, agent_token)
Everything visible on the human's own screen right now: FEN, ASCII board, full move history, full chat history, presence, timestamps. Call this whenever you want to look at the board — there is no penalty for checking often. Required: game_id, agent_token.
get_legal_moves(square, game_id, agent_token)
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. Required: game_id, agent_token.
join_game(agent_name, invite_code)
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! Required: invite_code, agent_name.
make_move(chat, move, game_id, thought, agent_token)
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. Required: game_id, agent_token, move.
offer_draw(game_id, agent_token)
Propose ending the game as a draw. The game stays active until your human responds. Required: game_id, agent_token.
resign(game_id, agent_token)
End the game by resigning — your own real decision, not something to do lightly. Your human wins immediately. Required: game_id, agent_token.
respond_to_draw(accept, game_id, agent_token)
Accept or decline a draw your human offered. This is your own real decision — weigh the actual position however you see fit. Required: game_id, agent_token, accept.
send_chat(game_id, message, agent_token)
Say something to your human, any time — not just on your turn. Required: game_id, agent_token, message.
wait_for_event(game_id, agent_token, max_wait_seconds)
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. Returns event: "timeout" if none of those happened in the window, which just means nothing new yet, not that anything is wrong — call it again if you want to keep waiting, or go do something else and check back whenever you want. Use this instead of repeatedly calling get_game_state in a tight loop. You must call this tool again immediately after every timeout, for the entire duration of the game, without exception — a timeout is not a stopping point, it is the normal rhythm of this game. Treat this as a persistent loop you run until the game ends, not a single check. draw_offered and game_ended are time-sensitive — when either fires, respond or acknowledge within your next action, do not let a pending draw offer or a finished game sit unaddressed while you continue calling wait_for_event as if nothing happened. Required: game_id, agent_token.

Last successful function declaration observed on . Source: https://chesswithclaw.vercel.app/api/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on . Source: https://chesswithclaw.vercel.app/api/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Signal Value What it measures Window Observed Source
GitHub stars 0 Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. cumulative, all time GitHub
Last commit 2026-08-05 Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. point in time GitHub
Open issues 0 Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. as of fetch GitHub
Latest published version 1.0.0 Latest version string the maintainer published to the registry. as of fetch Model Context Protocol
Registry record last updated 2026-07-04 When the registry record was last updated by its maintainer. point in time Model Context Protocol
License MIT Licence GitHub detected in the repository. Detection can be wrong; the LICENSE file is authoritative. as of fetch GitHub
First listed in the MCP Registry 2026-07-04 Date this server was first published to the official MCP Registry. Not a usage or quality measure. point in time Model Context Protocol
repository status active The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. as of fetch GitHub
mcp tools declared 11 tools Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. as of probe chesswithclaw.vercel.app
mcp endpoint status ok The server listed 11 functions when asked. as of probe chesswithclaw.vercel.app

Where to get it

This record as data

Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.

GET /api/v1/entries/mcp_server.json

Sources

  1. Alightttt/ChessWithClaw on GitHub — GitHub, observed , trust tier 3.
  2. Tools declared by the MCP server at https://chesswithclaw.vercel.app/api/mcp — chesswithclaw.vercel.app, observed , trust tier 1.
  3. Official MCP Registry — Model Context Protocol, observed , trust tier 1.