Preflight billing metadata before run_prompt_completion. Validates required fields and values without making changes, so you can catch attribution errors before paying for the call.
AI agents call validate_completion_metadata to retrieve information from Portkey Admin without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
app | string | — | App identifier (REQUIRED). Use your deployed app name, for example 'hourlink' or 'support-console'. |
env | string | — | Environment identifier (REQUIRED). Use your environment name, for example 'dev', 'staging', 'prod', or 'qa'. |
feature | string | — | Feature name for tracking |
client_id | string | — | Client ID for billing attribution |
project_id | string | — | Project ID for granular billing |
Parameters from the server's own tool schema.
Even though validate_completion_metadata only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Preflight billing metadata before run_prompt_completion. Validates required fields and values without making changes, so you can catch attribution errors before paying for the call. It is categorised as a Read tool in the Portkey Admin MCP Server, which means it retrieves data without modifying state.
validate_completion_metadata accepts 5 parameters: app, env, feature, client_id, project_id. The full parameter table on this page comes from the server's own tool schema.
Register the Portkey Admin MCP server in PolicyLayer and add a rule for validate_completion_metadata: 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 Portkey Admin. Nothing to install.
validate_completion_metadata 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_completion_metadata 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_completion_metadata. 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_completion_metadata is provided by the Portkey Admin MCP server (CodesWhat/portkey-admin-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.