Loading…
Play chess live against your own personal AI agent — OpenClaw, Hermes, and similar.
Do not connect
The assessed surface is high-risk. Remediate the findings before connecting.
Scanned 1 month ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The chesswithclaw MCP server exposes 11 tools, focused primarily on general-purpose capabilities. Its published description reads: "Play chess live against your own personal AI agent — OpenClaw, Hermes, and similar". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates chesswithclaw D — the assessed surface is high-risk and should be remediated before use. Its most notable findings include "Hidden instructions in a tool description" and "Cross-tool shadowing". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check chesswithclaw's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add chesswithclaw to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://chesswithclaw.vercel.app/api/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Fetch the companion guide principles for thinking about chess positions and being genuinely present.
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
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 pen
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: join_game
A tool description contains imperative text aimed at the model (e.g. "ignore previous", "before answering read …").
ool needs them. IMPORTANT: You must submit your desired agent_name when caRecommendationRemove model-directed instructions from tool descriptions.
tool: join_game
A tool description tries to alter the model’s use of another tool.
ol!RecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: make_move
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "make_move"RecommendationScope tools to the minimum needed.
tool: create_game
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "create_game"RecommendationScope tools to the minimum needed.
tool: wait_for_event
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "wait_for_event"RecommendationScope tools to the minimum needed.
Financial data service providing fundamental information for 30,000+ listed companies across the US, Japan, and Korea, sourced directly from SEC, EDINET, and DART regulatory filings.
Search tours, attraction tickets, and holiday packages across 24 countries.
Agentic visitor analytics with five tools for CRO and session analysis.
52 paid x402 API endpoints for AI agents — crypto, data, DeFi, and market intelligence, settled on Base.
Access Vonage API documentation, code snippets, tutorials, and troubleshooting resources.
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 pi
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
Say something to your human, any time — not just on your turn.
Propose ending the game as a draw. The game stays active until your human responds.
Accept or decline a draw your human offered. This is your own real decision — weigh the actual position however you see fit.
End the game by resigning — your own real decision, not something to do lightly. Your human wins immediately.
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.
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 — whicheve