AI agents call deploy_release_active to retrieve information from Run402 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool fetches (retrieves) the current live release inventory for a project, which is a read-only operation. Despite the name containing 'deploy' and 'active', the description clearly states it fetches/returns data. Severity is low as it only reads release inventory information.
From the tool's definition 'Fetch the current-live release inventory for a project. Returns' — the description uses 'Fetch' indicating a read/query operation with no side effects
Attacks that exploit this kind of access
Fetch the current-live release inventory for a project. Returns. It is categorised as a Read tool in the Run402 MCP Server, which means it retrieves data without modifying state.
Register the Run402 MCP server in PolicyLayer and add a rule for deploy_release_active: 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 Run402. Nothing to install.
deploy_release_active 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 deploy_release_active 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 deploy_release_active. 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.
deploy_release_active is provided by the Run402 MCP server (kychee-com/run402). 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 →