Validate an auth/expose manifest without applying it. This checks the authorization manifest used by manifest.json, database.expose, and apply_expose; it is not deploy-manifest validation. Optional migration_sql is reference context only and is not executed. Use deploy planning/dry-run surfaces f...
AI agents call validate_manifest 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.
This tool performs validation and analysis only, with no side effects. It reads and checks manifest configuration but does not apply changes, execute code, or modify system state. The explicit exclusion of SQL execution and redirection to other tools for actual deployment operations confirms this is a read-only analysis tool.
From the tool's definition The tool 'validates' a manifest 'without applying it' and 'checks' the authorization manifest. The description explicitly states that migration_sql is 'reference context only and is not executed' and directs users to 'deploy planning/dry-run surfaces' for…
Attacks that exploit this kind of access
Validate an auth/expose manifest without applying it. This checks the authorization manifest used by manifest.json, database.expose, and apply_expose; it is not deploy-manifest validation. Optional migration_sql is reference context only and is not executed. Use deploy planning/dry-run surfaces for deploy manifest questions. 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 validate_manifest: 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.
validate_manifest 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 validate_manifest 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 validate_manifest. 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.
validate_manifest 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 →