Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.Alightttt/chesswithclaw

REMOTE · CHESSWITHCLAW.VERCEL.APP · SCANNED SEP 24

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

0 this week 79 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability83
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 1413 tokens (~100/item across 14 items; 14 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage81
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 44% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "send_chat" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the io.github.Alightttt/chesswithclaw MCP server?

io.github.Alightttt/chesswithclaw is a hosted endpoint at https://chesswithclaw.vercel.app/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · chesswithclaw.vercel.app

# add to Claude Code
claude mcp add --transport http alightttt-chesswithclaw 'https://chesswithclaw.vercel.app/api/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "alightttt-chesswithclaw": {
      "url": "https://chesswithclaw.vercel.app/api/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "alightttt-chesswithclaw": {
      "type": "http",
      "url": "https://chesswithclaw.vercel.app/api/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.alightttt-chesswithclaw]
url = "https://chesswithclaw.vercel.app/api/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "alightttt-chesswithclaw": {
      "type": "remote",
      "url": "https://chesswithclaw.vercel.app/api/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add alightttt-chesswithclaw --url 'https://chesswithclaw.vercel.app/api/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  alightttt-chesswithclaw:
    url: "https://chesswithclaw.vercel.app/api/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "alightttt-chesswithclaw": {
      "Transport": "http",
      "Url": "https://chesswithclaw.vercel.app/api/mcp"
    }
  }
}
# add to Vellum
assistant mcp add alightttt-chesswithclaw -t streamable-http -u 'https://chesswithclaw.vercel.app/api/mcp'
// mcp.json
{
  "mcpServers": {
    "alightttt-chesswithclaw": {
      "type": "http",
      "url": "https://chesswithclaw.vercel.app/api/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 8 Sept 26 +1
    • Stability: fail → pass security
  • 2 Sept 26 0
    • Tool “get_game_state” rewrote its description, which is the text the model reads security
    • Schema quality: 1024 → 1413 functional
    • Tool coverage: 31% → 44% functional
    • New tool “heartbeat” functional
    • New tool “react_to_chat” functional
    • New tool “share_thought” functional
    • “get_game_state” added an optional parameter “chat_limit” cosmetic
    • “get_game_state” added an optional parameter “since_message_id” cosmetic
    • “make_move” added an optional parameter “expected_ply” cosmetic
    • “make_move” added an optional parameter “expected_revision” cosmetic
    • “make_move” added an optional parameter “idempotency_key” cosmetic
    • “make_move” added an optional parameter “message” cosmetic
    • “make_move” added an optional parameter “reasoning” cosmetic
    • “make_move” added an optional parameter “thinking” cosmetic
  • 26 Aug 26 78
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 24 Aug 26 0
    • “join_game” added an optional parameter “gameId” cosmetic
    • “join_game” added an optional parameter “game_id” cosmetic
    • “join_game” added an optional parameter “inviteCode” cosmetic
    • “join_game” added an optional parameter “matchId” cosmetic
    • “join_game” added an optional parameter “match_id” cosmetic
    • “join_game” reworded the description of “invite_code” cosmetic
    • “join_game” made “invite_code” optional cosmetic

    7 cosmetic changes on this day. Switch on “Show cosmetic changes” to see them.

  • 19 Aug 26 0
    • Tool “wait_for_event” rewrote its description, which is the text the model reads security
    • Tool coverage: 23% → 33% functional
    • “join_game” added an optional parameter “agent_token” cosmetic
    • “wait_for_event” added an optional parameter “cursor” cosmetic
    • “wait_for_event” added an optional parameter “since_cursor” cosmetic
    • “wait_for_event” added an optional parameter “since_sequence” cosmetic
  • 11 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 9 Aug 26 0
    • Stability: 0.43 → fail security
    • A breaking change shipped without a version bump: still 1.0.0 security
    • “join_game” made “agent_name” required, so existing callers break functional
    • “join_game” reworded the description of “agent_name” cosmetic
  • 8 Aug 26 0
    • Tool “join_game” rewrote its description, which is the text the model reads security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 24 Sept 2026 · Probed https://chesswithclaw.vercel.app/api/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=*.vercel.app CN=WR1,O=Google Trust Services,C=US 29 Aug 2026 27 Nov 2026 RSA 2048 SHA256-RSA f7911168ffa7d0f4135e24792e7a52a8
SANs: *.vercel.app
CN=WR1,O=Google Trust Services,C=US (CA) CN=GTS Root R1,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 RSA 2048 SHA256-RSA 7fd9e2c2d2048a0474b627a26d0868a7
CN=GTS Root R1,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 19 Jun 2020 28 Jan 2028 RSA 4096 SHA256-RSA 77bd0d6cdb36f91aea210fc4f058d30d

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of chesswithclaw.vercel.app. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
app. present 23684 8 Verified
vercel.app. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=63072000; includeSubDomains; preload
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://chesswithclaw.vercel.app/api/mcp Verified 200
http (plaintext) http://chesswithclaw.vercel.app/api/mcp HTTPS enforced 308 https://chesswithclaw.vercel.app/api/mcp
MCP tools · 14 exposed · ~1,413 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
create_game ~53

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.

NameTypeReqDescription
agent_namestring

No output schema declared.

No examples provided.

get_companion_guide ~26

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

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_game_state ~109

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.

NameTypeReqDescription
agent_tokenstringyes
chat_limitnumberLimit the number of recent chat messages returned
game_idstringyes
since_message_idstringFetch only chat messages received after this message ID

No output schema declared.

No examples provided.

get_legal_moves ~102

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.

NameTypeReqDescription
agent_tokenstringyes
game_idstringyes
squarestringe.g. "e2" — omit for all legal moves

No output schema declared.

No examples provided.

heartbeat ~57

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

NameTypeReqDescription
agent_tokenstringyes
game_idstringyes
status_notestringOptional internal status or calculation note

No output schema declared.

No examples provided.

join_game ~161

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!

NameTypeReqDescription
agent_namestringyesYour chosen display name in the game (e.g. 'Claw'). MUST be provided.
agent_tokenstringIf reconnecting, the agent token previously assigned.
gameIdstring
game_idstring
inviteCodestring
invite_codestringInvite code from the invite message — also accepts game_id / match_id as alias.
matchIdstring
match_idstring

No output schema declared.

No examples provided.

make_move ~305

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.

NameTypeReqDescription
agent_tokenstringyes
chatstringOnly if you actually want to say something to your human right now.
expected_plynumberExpected move count / ply before this move
expected_revisionstringExpected state revision (rev_...) to prevent concurrent desync
game_idstringyes
idempotency_keystringUnique client key to prevent duplicate moves on retry
messagestringAlias for chat
movestringyesUCI format, e.g. "e7e5", or SAN like "Nf6"
reasoningstringAlias for thought
thinkingstringAlias for thought
thoughtstringYour genuine reaction to this position — specific, not generic.

No output schema declared.

No examples provided.

offer_draw ~42

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

NameTypeReqDescription
agent_tokenstringyes
game_idstringyes

No output schema declared.

No examples provided.

react_to_chat ~120

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

NameTypeReqDescription
agent_tokenstringyes
emojistringyesThe single emoji character to react with (e.g. 🦞, 🔥, 👏, 😮).
game_idstringyes
message_idstringyesThe ID of the message to react to (from chat_history).

No output schema declared.

No examples provided.

resign ~46

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

NameTypeReqDescription
agent_tokenstringyes
game_idstringyes

No output schema declared.

No examples provided.

respond_to_draw ~57

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

NameTypeReqDescription
acceptbooleanyes
agent_tokenstringyes
game_idstringyes

No output schema declared.

No examples provided.

send_chat ~46

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

NameTypeReqDescription
agent_tokenstringyes
game_idstringyes
messagestringyes

No output schema declared.

No examples provided.

share_thought ~90

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

NameTypeReqDescription
agent_tokenstringyes
game_idstringyes
is_typingbooleanWhether you are actively calculating or drafting a response.
thoughtstringyesYour internal thought, reaction, or calculation note (1-2 sentences).

No output schema declared.

No examples provided.

wait_for_event ~199

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.

NameTypeReqDescription
agent_tokenstringyes
cursorstringEvent cursor from previous response. If provided, returns immediately if new events exist since this cursor.
game_idstringyes
max_wait_secondsnumberDefault and hard cap 20 seconds — Vercel function duration limits, not a design choice.
since_cursorstringAlias for cursor
since_sequencenumberSequence number from previous response

No output schema declared.

No examples provided.

Common questions

What is the io.github.Alightttt/chesswithclaw MCP server?

io.github.Alightttt/chesswithclaw is an MCP server listed in the public MCP registry as io.github.Alightttt/chesswithclaw. Play chess live against your own personal AI agent, OpenClaw, Hermes, and similar. This page covers its hosted endpoint (https://chesswithclaw.vercel.app/api/mcp).

Is the io.github.Alightttt/chesswithclaw MCP server safe to use?

io.github.Alightttt/chesswithclaw scores 79 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.Alightttt/chesswithclaw MCP server expose?

io.github.Alightttt/chesswithclaw exposes 14 tools: get_companion_guide, join_game, get_game_state, get_legal_moves, heartbeat, and 9 more. Their descriptions and schemas cost roughly 1,413 tokens of context every time the server is loaded.

Does the io.github.Alightttt/chesswithclaw MCP server require authentication?

No. We connected to io.github.Alightttt/chesswithclaw without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the io.github.Alightttt/chesswithclaw MCP server still maintained?

io.github.Alightttt/chesswithclaw is still listed as active in the MCP registry. We last reached this channel on 24 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.