Pause an active download
AI agents invoke hydra_pause_download to trigger actions in Hydra Bridge. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Pausing a download is an external operation that affects the state of the Hydra Launcher application. It is not a simple read, nor does it delete or irreversibly destroy data. It falls under Execute as it triggers a state change in an external system (the download manager). The blast radius is low since pausing is easily reversible.
From the tool's definition 'Pause an active download' — triggers an external operation (pausing a running download process in Hydra Launcher)
Attacks that exploit this kind of access
Pause an active download. It is categorised as a Execute tool in the Hydra Bridge MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Hydra Bridge MCP server in PolicyLayer and add a rule for hydra_pause_download: 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_pause_download is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the hydra_pause_download 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_pause_download. 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_pause_download 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 →