Revoke the current access token
AI agents call revoke_token to permanently remove resources in Lichess Integration — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Revoking an access token is an irreversible action — once revoked, the token cannot be restored. This would immediately terminate the authenticated session and could lock the AI agent (and user) out of the Lichess integration until a new token is obtained. This qualifies as Destructive due to its irreversible nature and high blast radius.
From the tool's definition Revoke the current access token
Attacks that exploit this kind of access
Revoke the current access token. It is categorised as a Destructive tool in the Lichess Integration MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Lichess Integration MCP server in PolicyLayer and add a rule for revoke_token: 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 Integration. Nothing to install.
revoke_token is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the revoke_token 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 revoke_token. 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.
revoke_token is provided by the Lichess Integration MCP server (karayaman/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 →