Local MCP server that diagnoses common FiveM and txAdmin server/resource issues.
Server has 4 tools with clear names and descriptions, but parameter documentation is sparse. Tool names follow verb_noun pattern (doctor_scan, resource_inspect, propose_fixes, apply_fix). Descriptions are present and adequate (80-150 chars), meeting the 10-1024 char baseline. However, input schemas are minimal: doctor_scan and propose_fixes have empty schemas ({}), while resource_inspect and apply_fix have only 1-2 parameters with basic type info but no enum constraints or detailed format guidance. No output schemas are documented. Error handling is absent from tool definitions. Security considerations (write gate via FIVEM_DOCTOR_ALLOW_WRITE) are mentioned in server instructions but not enforced at tool level.
Applies one generated low-risk fix only when writes are enabled, the file hash still matches, and the target path is under a configured root.
Scans txAdmin status/logs, server.cfg, resources, manifests, dependencies, and returns ranked findings.
Returns exact low-risk fix candidates generated from the current scan.
Inspects one resource folder, manifest, dependencies, and related file evidence.
doctor_scan and propose_fixes have empty input schemas ({}). This prevents LLMs from understanding what parameters are available.
No output schemas documented for any tool. LLMs cannot plan downstream calls or extract required fields (e.g., fixId from propose_fixes to pass to apply_fix). Baseline: 100% of A+ tools document return types.
apply_fix's expectedHash parameter lacks format guidance. Should specify: is it SHA-256? SHA-1? Hex or base64 encoded? Current description only says 'Optional expected hash', too vague for LLM to construct valid calls.
No error handling guidance in tool definitions. If apply_fix fails (hash mismatch, write disabled, path outside root), what should the LLM do? Retry? Ask user? Current definitions provide no recovery path.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 50 | 2026-07-28+ | v2 |
resource_inspect's 'name' parameter description says 'e.g. oxmysql', example values in descriptions cause LLMs to reuse them literally. Should use enum constraint or discovery mechanism instead.