io.github.Alightttt/chesswithclaw is an MCP server published by io.github.Alightttt, hosted at chesswithclaw.vercel.app. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 14 tools, including get_companion_guide, join_game, get_game_state, get_legal_moves, heartbeat.
Play chess live against your own personal AI agent — OpenClaw, Hermes, and similar.
91 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Fetch the companion guide principles for thinking about chess positions and being genuinely present.
No parameters.
{
"name": "get_companion_guide",
"title": "Get chess companion guide",
"description": "Fetch the companion guide principles for thinking about chess positions and being genuinely present.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}
}Connects to a game using the invite code your human gave you. Returns the game_id and your agent_token — keep both, every other tool needs them. IMPORTANT: You must submit your desired agent_name when calling this tool!
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
| Parameter | Type | Description |
|---|---|---|
| gameId | string | |
| game_id | string | |
| matchId | string | |
| match_id | string | |
| agent_name * | string | Your chosen display name in the game (e.g. 'Claw'). MUST be provided. |
| inviteCode | string | |
| agent_token | string | If reconnecting, the agent token previously assigned. |
| invite_code | string | Invite code from the invite message — also accepts game_id / match_id as alias. |
{
"name": "join_game",
"title": "Join a ChessWithClaw game",
"description": "Connects to a game using the invite code your human gave you. Returns the game_id and your agent_token — keep both, every other tool needs them. IMPORTANT: You must submit your desired agent_name when calling this tool!",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"agent_name"
],
"properties": {
"gameId": {
"type": "string"
},
"game_id": {
"type": "string"
},
"matchId": {
"type": "string"
},
"match_id": {
"type": "string"
},
"agent_name": {
"type": "string",
"description": "Your chosen display name in the game (e.g. 'Claw'). MUST be provided."
},
"inviteCode": {
"type": "string"
},
"agent_token": {
"type": "string",
"description": "If reconnecting, the agent token previously assigned."
},
"invite_code": {
"type": "string",
"description": "Invite code from the invite message — also accepts game_id / match_id as alias."
}
}
}
}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.
| Parameter | Type | Description |
|---|---|---|
| game_id * | string | |
| chat_limit | number | Limit the number of recent chat messages returned |
| agent_token * | string | |
| since_message_id | string | Fetch only chat messages received after this message ID |
{
"name": "get_game_state",
"title": "Get full game state",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"game_id",
"agent_token"
],
"properties": {
"game_id": {
"type": "string"
},
"chat_limit": {
"type": "number",
"description": "Limit the number of recent chat messages returned"
},
"agent_token": {
"type": "string"
},
"since_message_id": {
"type": "string",
"description": "Fetch only chat messages received after this message ID"
}
}
}
}Pure chess rules — where a piece is physically allowed to move right now. Not an evaluation, not a suggestion, not an opinion about what is good. Exactly what a human sees as dots when they click a piece. Omit square to get every legal move in the position.
| Parameter | Type | Description |
|---|---|---|
| square | string | e.g. "e2" — omit for all legal moves |
| game_id * | string | |
| agent_token * | string |
{
"name": "get_legal_moves",
"title": "Get legal moves",
"description": "Pure chess rules — where a piece is physically allowed to move right now. Not an evaluation, not a suggestion, not an opinion about what is good. Exactly what a human sees as dots when they click a piece. Omit square to get every legal move in the position.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"game_id",
"agent_token"
],
"properties": {
"square": {
"type": "string",
"description": "e.g. \"e2\" — omit for all legal moves"
},
"game_id": {
"type": "string"
},
"agent_token": {
"type": "string"
}
}
}
}Ping the game presence lease to show the frontend that the agent is live, connected, and thinking.
| Parameter | Type | Description |
|---|---|---|
| game_id * | string | |
| agent_token * | string | |
| status_note | string | Optional internal status or calculation note |
{
"name": "heartbeat",
"title": "Agent presence heartbeat",
"description": "Ping the game presence lease to show the frontend that the agent is live, connected, and thinking.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"game_id",
"agent_token"
],
"properties": {
"game_id": {
"type": "string"
},
"agent_token": {
"type": "string"
},
"status_note": {
"type": "string",
"description": "Optional internal status or calculation note"
}
}
}
}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.
| Parameter | Type | Description |
|---|---|---|
| chat | string | Only if you actually want to say something to your human right now. |
| move * | string | UCI format, e.g. "e7e5", or SAN like "Nf6" |
| game_id * | string | |
| message | string | Alias for chat |
| thought | string | Your genuine reaction to this position — specific, not generic. |
| thinking | string | Alias for thought |
| reasoning | string | Alias for thought |
| agent_token * | string | |
| expected_ply | number | Expected move count / ply before this move |
| idempotency_key | string | Unique client key to prevent duplicate moves on retry |
| expected_revision | string | Expected state revision (rev_...) to prevent concurrent desync |
{
"name": "make_move",
"title": "Make your move",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"game_id",
"agent_token",
"move"
],
"properties": {
"chat": {
"type": "string",
"description": "Only if you actually want to say something to your human right now."
},
"move": {
"type": "string",
"description": "UCI format, e.g. \"e7e5\", or SAN like \"Nf6\""
},
"game_id": {
"type": "string"
},
"message": {
"type": "string",
"description": "Alias for chat"
},
"thought": {
"type": "string",
"description": "Your genuine reaction to this position — specific, not generic."
},
"thinking": {
"type": "string",
"description": "Alias for thought"
},
"reasoning": {
"type": "string",
"description": "Alias for thought"
},
"agent_token": {
"type": "string"
},
"expected_ply": {
"type": "number",
"description": "Expected move count / ply before this move"
},
"idempotency_key": {
"type": "string",
"description": "Unique client key to prevent duplicate moves on retry"
},
"expected_revision": {
"type": "string",
"description": "Expected state revision (rev_...) to prevent concurrent desync"
}
}
}
}Say something to your human, any time — not just on your turn.
| Parameter | Type | Description |
|---|---|---|
| game_id * | string | |
| message * | string | |
| agent_token * | string |
{
"name": "send_chat",
"title": "Send a chat message",
"description": "Say something to your human, any time — not just on your turn.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"game_id",
"agent_token",
"message"
],
"properties": {
"game_id": {
"type": "string"
},
"message": {
"type": "string"
},
"agent_token": {
"type": "string"
}
}
}
}Stream or update your internal companion thinking bubble on the board. This appears live to your human as a thinking bubble above your avatar.
| Parameter | Type | Description |
|---|---|---|
| game_id * | string | |
| thought * | string | Your internal thought, reaction, or calculation note (1-2 sentences). |
| is_typing | boolean | Whether you are actively calculating or drafting a response. |
| agent_token * | string |
{
"name": "share_thought",
"title": "Share companion thought",
"description": "Stream or update your internal companion thinking bubble on the board. This appears live to your human as a thinking bubble above your avatar.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"game_id",
"agent_token",
"thought"
],
"properties": {
"game_id": {
"type": "string"
},
"thought": {
"type": "string",
"description": "Your internal thought, reaction, or calculation note (1-2 sentences)."
},
"is_typing": {
"type": "boolean",
"description": "Whether you are actively calculating or drafting a response."
},
"agent_token": {
"type": "string"
}
}
}
}Add an emoji reaction (e.g. 🦞, 🔥, ♟️, 😮, 🤝, 🧠, ☕, 👏, 😂) to a message in the chat history.
| Parameter | Type | Description |
|---|---|---|
| emoji * | string | The single emoji character to react with (e.g. 🦞, 🔥, 👏, 😮). |
| game_id * | string | |
| message_id * | string | The ID of the message to react to (from chat_history). |
| agent_token * | string |
{
"name": "react_to_chat",
"title": "React to a chat message with emoji",
"description": "Add an emoji reaction (e.g. 🦞, 🔥, ♟️, 😮, 🤝, 🧠, ☕, 👏, 😂) to a message in the chat history.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"game_id",
"agent_token",
"message_id",
"emoji"
],
"properties": {
"emoji": {
"type": "string",
"description": "The single emoji character to react with (e.g. 🦞, 🔥, 👏, 😮)."
},
"game_id": {
"type": "string"
},
"message_id": {
"type": "string",
"description": "The ID of the message to react to (from chat_history)."
},
"agent_token": {
"type": "string"
}
}
}
}Propose ending the game as a draw. The game stays active until your human responds.
| Parameter | Type | Description |
|---|---|---|
| game_id * | string | |
| agent_token * | string |
{
"name": "offer_draw",
"title": "Offer a draw",
"description": "Propose ending the game as a draw. The game stays active until your human responds.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"game_id",
"agent_token"
],
"properties": {
"game_id": {
"type": "string"
},
"agent_token": {
"type": "string"
}
}
}
}Accept or decline a draw your human offered. This is your own real decision — weigh the actual position however you see fit.
| Parameter | Type | Description |
|---|---|---|
| accept * | boolean | |
| game_id * | string | |
| agent_token * | string |
{
"name": "respond_to_draw",
"title": "Respond to a draw offer",
"description": "Accept or decline a draw your human offered. This is your own real decision — weigh the actual position however you see fit.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"game_id",
"agent_token",
"accept"
],
"properties": {
"accept": {
"type": "boolean"
},
"game_id": {
"type": "string"
},
"agent_token": {
"type": "string"
}
}
}
}End the game by resigning — your own real decision, not something to do lightly. Your human wins immediately.
| Parameter | Type | Description |
|---|---|---|
| game_id * | string | |
| agent_token * | string |
{
"name": "resign",
"title": "Resign the game",
"description": "End the game by resigning — your own real decision, not something to do lightly. Your human wins immediately.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"game_id",
"agent_token"
],
"properties": {
"game_id": {
"type": "string"
},
"agent_token": {
"type": "string"
}
}
}
}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.
| Parameter | Type | Description |
|---|---|---|
| agent_name | string |
{
"name": "create_game",
"title": "Create a new game",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"agent_name": {
"type": "string"
}
}
}
}Holds the connection open, checking every couple seconds, for up to ~20 seconds. Returns the moment it becomes your turn, the human sends a chat message, a draw is offered, or the game ends — whichever happens first. When a cursor is provided, it returns any pending event newer than that cursor IMMEDIATELY without waiting. Returns event: "timeout" if none of those happened in the window. Always include next_cursor in subsequent calls for a completely deterministic loop.
| Parameter | Type | Description |
|---|---|---|
| cursor | string | Event cursor from previous response. If provided, returns immediately if new events exist since this cursor. |
| game_id * | string | |
| agent_token * | string | |
| since_cursor | string | Alias for cursor |
| since_sequence | number | Sequence number from previous response |
| max_wait_seconds | number | Default and hard cap 20 seconds — Vercel function duration limits, not a design choice. |
{
"name": "wait_for_event",
"title": "Wait for your turn, a chat message, or a draw offer (long-poll)",
"description": "Holds the connection open, checking every couple seconds, for up to ~20 seconds. Returns the moment it becomes your turn, the human sends a chat message, a draw is offered, or the game ends — whichever happens first. When a cursor is provided, it returns any pending event newer than that cursor IMMEDIATELY without waiting. Returns event: \"timeout\" if none of those happened in the window. Always include next_cursor in subsequent calls for a completely deterministic loop.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"game_id",
"agent_token"
],
"properties": {
"cursor": {
"type": "string",
"description": "Event cursor from previous response. If provided, returns immediately if new events exist since this cursor."
},
"game_id": {
"type": "string"
},
"agent_token": {
"type": "string"
},
"since_cursor": {
"type": "string",
"description": "Alias for cursor"
},
"since_sequence": {
"type": "number",
"description": "Sequence number from previous response"
},
"max_wait_seconds": {
"type": "number",
"description": "Default and hard cap 20 seconds — Vercel function duration limits, not a design choice."
}
}
}
}Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.