Request, accept, or decline a takeback (undo last move) in an active Lichess chess game.
AI agents call lichess_takeback 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.
Even though lichess_takeback only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Request, accept, or decline a takeback (undo last move) in an active Lichess chess game. 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_takeback: 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_takeback 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_takeback 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_takeback. 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_takeback 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 →