# run_prompt_completion

Execute a prompt against the configured model and return the completion. This makes a billable model call, so use render_prompt first when you want to check the template and validate_completion_metadata when billing fields are uncertain.

Agent View of the PolicyLayer registry record for `run_prompt_completion`. HTML page: https://policylayer.com/tools/codeswhat-portkey-admin-mcp/run-prompt-completion

## Facts

- Tool: `run_prompt_completion`
- Server: Portkey Admin (`codeswhat/portkey-admin-mcp`) — https://policylayer.com/tools/codeswhat-portkey-admin-mcp.md
- Homepage: https://github.com/CodesWhat/portkey-admin-mcp
- Risk category: Execute (High risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run_prompt_completion",
    "arguments": {}
  }
}
```

## Why run_prompt_completion is rated High

The tool executes a live model call which triggers an external operation with real-world effects. It is explicitly noted as 'billable', meaning it incurs financial cost, but the primary action is execution of an external model API call rather than a direct financial transaction (payment, refund, trade).

From the tool's own definition: "Execute a prompt against the configured model and return the completion. This makes a billable model call"

## Use case

AI agents invoke run_prompt_completion to trigger actions in Portkey Admin. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Portkey Admin:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_prompt_completion": {
      "limits": [
        {
          "counter": "run_prompt_completion_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Portkey Admin (155)

- `cancel_log_export` — Destructive — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/cancel-log-export.md
- `delete_api_key` — Destructive — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/delete-api-key.md
- `delete_collection` — Destructive — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/delete-collection.md
- `delete_config` — Destructive — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/delete-config.md
- `delete_guardrail` — Destructive — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/delete-guardrail.md
- `delete_integration` — Destructive — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/delete-integration.md
- `delete_integration_model` — Destructive — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/delete-integration-model.md
- `delete_mcp_integration` — Destructive — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/delete-mcp-integration.md
- `delete_mcp_server` — Destructive — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/delete-mcp-server.md
- `delete_prompt` — Destructive — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/delete-prompt.md
- `delete_prompt_label` — Destructive — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/delete-prompt-label.md
- `delete_prompt_partial` — Destructive — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/delete-prompt-partial.md
- `delete_provider` — Destructive — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/delete-provider.md
- `delete_rate_limit` — Destructive — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/delete-rate-limit.md
- `delete_secret_reference` — Destructive — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/delete-secret-reference.md
- `delete_usage_limit` — Destructive — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/delete-usage-limit.md
- `delete_user` — Destructive — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/delete-user.md
- `delete_user_invite` — Destructive — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/delete-user-invite.md
- `delete_virtual_key` — Destructive — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/delete-virtual-key.md
- `delete_workspace` — Destructive — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/delete-workspace.md
- `remove_workspace_member` — Destructive — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/remove-workspace-member.md
- `start_log_export` — Execute — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/start-log-export.md
- `test_mcp_server` — Execute — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/test-mcp-server.md
- `download_log_export` — Read — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/download-log-export.md
- `get_analytics_group_metadata` — Read — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/get-analytics-group-metadata.md
- `get_analytics_group_models` — Read — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/get-analytics-group-models.md
- `get_analytics_group_users` — Read — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/get-analytics-group-users.md
- `get_api_key` — Read — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/get-api-key.md
- `get_cache_hit_latency` — Read — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/get-cache-hit-latency.md
- `get_cache_hit_rate` — Read — https://policylayer.com/tools/codeswhat-portkey-admin-mcp/get-cache-hit-rate.md
- …and 125 more: https://policylayer.com/tools/codeswhat-portkey-admin-mcp.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=codeswhat-portkey-admin-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/codeswhat-portkey-admin-mcp
