MCP server providing calculator operations and Meta Ads API integration for managing ad accounts, campaigns, ad sets, and ads
Server has 5 tools with basic schemas and descriptions, but significant gaps prevent higher scores. Calculator tools (add, calculate) are simple and well-defined. Meta Ads tools have descriptions but lack critical details: no error recovery guidance, no pagination documentation despite list operations, no permission/scope declarations, and hardcoded credentials exposed in source. Descriptions average ~100 chars (below 194-char baseline). Parameter descriptions exist but are minimal. No output schemas documented. No tool annotations (readOnlyHint, etc.). Overall structure is present but production-readiness is compromised by security and completeness issues.
Simple addition tool that adds two numbers
Calculator tool with multiple operations (add, subtract, multiply, divide)
Retrieve detailed information about a specific Meta ad account including status, spending, balance, currency, timezone, country, spend cap, and owner
Fetch ad accounts for a Meta user with details including account status, spending, balance, currency, and timezone
Retrieve campaigns from a Meta ad account with optional status filtering
Hardcoded Meta API credentials (appId, accessToken) exposed in source code. Credentials must use server-side secret injection via environment variables or vault. Agent traces log all parameters, secrets in code leak into logs and version control.
Meta Ads tools lack pagination documentation and result limits. metaAdsGetAdAccounts accepts 'limit' parameter but no documentation of max value, default behavior, or next_cursor/offset for large result sets. LLMs cannot plan multi-page retrieval.
No error recovery guidance in tool descriptions. Meta Ads tools return JSON errors but do not tell LLM what to do next (retry, ask user, abort). Error responses lack categorization (retryable vs fatal).
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 50 | 2026-07-28+ | v2 |
No permission/scope declarations. Meta Ads tools do not declare required permissions (e.g., 'read:ads', 'write:campaigns'). Agents cannot configure least-privilege access or understand audit implications.
Output schemas not documented. Tool descriptions do not specify what fields are returned or their types. LLMs cannot plan downstream tool calls or extract required data (e.g., accountId for chaining).