Stream the live board state, moves, and game events for an ongoing Lichess chess game. Get real-time updates including position, clocks, and chat.
AI agents call lichess_stream_game to retrieve information from Lichess MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads/queries the state of a chess game in progress. It does not create, modify, delete, or execute any actions that change game state or external systems. Streaming live data and retrieving game events is a read operation.
From the tool's definition Tool streams and retrieves live board state, moves, and game events for an ongoing game—pure observation without modification.
Attacks that exploit this kind of access
Stream the live board state, moves, and game events for an ongoing Lichess chess game. Get real-time updates including position, clocks, and chat. It is categorised as a Read tool in the Lichess MCP MCP Server, which means it retrieves data without modifying state.
Register the Lichess MCP server in PolicyLayer and add a rule for lichess_stream_game: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Lichess MCP. Nothing to install.
lichess_stream_game is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the lichess_stream_game rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for lichess_stream_game. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
lichess_stream_game is provided by the Lichess MCP server (jamespdaily/lichess-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →