AI agents call deploy_release_get 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 only retrieves/fetches data about a release — it does not modify, execute, or delete anything. The word 'Fetch' and 'Returns' confirm this is a read-only operation. Severity is low since it's read-only, though it does return potentially sensitive data like secret keys, which slightly elevates concern but not the category.
From the tool's definition Fetch a release inventory by id. Returns release metadata, effective/desired state kind, site path inventory, function inventory, secret keys, subdomains, and applied migrations.
Attacks that exploit this kind of access
Fetch a release inventory by id. Returns release metadata, effective/desired state kind, site path inventory, function inventory, secret keys, subdomains, and applied migrations. Use. 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_get: 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_get 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_get 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_get. 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_get 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 →