Add a custom (non-catalogue) game to the library by specifying its executable path
AI agents use hydra_import_game to create or update resources in Hydra Bridge — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Hydra Bridge environment.
The tool creates new data (a game library entry) rather than merely reading or querying it. It does not delete, overwrite irreversibly, execute arbitrary code, or move money. While it takes a file path argument (the executable), the tool itself does not execute that executable — it merely registers it in the library.
From the tool's definition Tool description states 'Add a custom (non-catalogue) game to the library' — this creates a new entry in the game library, a reversible modification of application state.
Attacks that exploit this kind of access
Add a custom (non-catalogue) game to the library by specifying its executable path. It is categorised as a Write tool in the Hydra Bridge MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Hydra Bridge MCP server in PolicyLayer and add a rule for hydra_import_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 Hydra Bridge. Nothing to install.
hydra_import_game is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the hydra_import_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 hydra_import_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.
hydra_import_game is provided by the Hydra Bridge MCP server (kleirrampage45/hydra-bridge). 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 →