MCP server that generates media (images, audio, video) and posts to Twitter/X
Critical gaps across all dimensions. Tool definitions lack proper schemas, descriptions are minimal (10-20 chars), and no input validation or error handling visible. The server exposes credentials as environment variables (correct) but tool implementations show no parameter validation, error recovery, or output structure documentation. Both tools are write operations with no confirmation or dry-run support. Code is largely commented out, suggesting incomplete implementation.
Create a post on X (formerly Twitter)
Generate image, audio, and video from a prompt
Tool descriptions are critically short (10-20 chars). 'Generate image, audio, and video from a prompt' and 'Create a post on X (formerly Twitter)' lack context on WHEN to use, WHAT it returns, and any prerequisites. Baseline for A+ tools is 50-200 chars with explicit intent guidance.
Input schemas visible but lack proper type definitions and constraints. 'prompt' and 'status' parameters have descriptions but no enum constraints, length limits, or format specifications. LLMs will hallucinate invalid values without formal constraints.
No output schema documentation visible. Tool implementations return generic text responses without structured fields. LLMs cannot plan downstream calls or extract required data (e.g., video URL, post ID) from unstructured text.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 33 | 2026-07-28+ | v2 |
Both tools are destructive write operations (WRITE risk) with no confirmation, dry-run, or idempotency support. createPost will duplicate tweets on retry; generateMediaVideo may consume quota repeatedly. No error recovery guidance.
No input validation or error handling visible in tool implementations. createPost passes status directly to Twitter API without sanitizing for length, special characters, or rate limits. generateMediaVideo has no error messages or recovery guidance.