Pre-flight check for deploy_app: surfaces the caller
AI agents call check_deployment_readiness to retrieve information from Manifest MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to be a diagnostic/validation check that queries deployment readiness status and returns information to the caller. It performs no write, execute, or destructive operations—it simply surfaces (returns/displays) readiness state. The 'pre-flight check' pattern is standard for read-only validation before allowing other operations.
From the tool's definition Tool description states 'Pre-flight check' which performs validation/inspection without modification. The verb 'surfaces' indicates information retrieval. No descriptions of side effects, state changes, or destructive operations present.
Attacks that exploit this kind of access
Pre-flight check for deploy_app: surfaces the caller. It is categorised as a Read tool in the Manifest MCP MCP Server, which means it retrieves data without modifying state.
Register the Manifest MCP server in PolicyLayer and add a rule for check_deployment_readiness: 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 Manifest MCP. Nothing to install.
check_deployment_readiness 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 check_deployment_readiness 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 check_deployment_readiness. 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.
check_deployment_readiness is provided by the Manifest MCP server (manifest-network/manifest-mcp-mono). 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 →