export_ongoing_game · Lichess Integration MCP: Risk & Policy

WHAT IT DOES

What export_ongoing_game does on Lichess Integration

AI agents call export_ongoing_game to retrieve information from Lichess Integration without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

PARAMETERS

Parameter	Type	Required	Description
`tags`	boolean	—	Include the PGN tags
`evals`	boolean	—	Include analysis evaluation comments
`moves`	boolean	—	Include the PGN moves
`clocks`	boolean	—	Include clock comments in the PGN moves
`opening`	boolean	—	Include opening name
`username`	string	—	The username
`pgnInJson`	boolean	—	Include the full PGN within the JSON response

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why export_ongoing_game needs a policy

This tool retrieves/exports current game data for a user. It is a read-only operation that queries and returns game state without modifying any data or causing side effects.

From the tool's definition Export ongoing game of a user

Attacks that exploit this kind of access

Questions about export_ongoing_game

What does the export_ongoing_game tool do? +

Export ongoing game of a user. It is categorised as a Read tool in the Lichess Integration MCP Server, which means it retrieves data without modifying state.

What parameters does export_ongoing_game accept? +

export_ongoing_game accepts 7 parameters: tags, evals, moves, clocks, opening, username, pgnInJson. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on export_ongoing_game? +

Register the Lichess Integration MCP server in PolicyLayer and add a rule for export_ongoing_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 Integration. Nothing to install.

What risk level is export_ongoing_game? +

export_ongoing_game is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit export_ongoing_game? +

Yes. Add a rate_limit block to the export_ongoing_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.

How do I block export_ongoing_game completely? +

Set action: deny in the PolicyLayer policy for export_ongoing_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.

What MCP server provides export_ongoing_game? +

export_ongoing_game 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.