Open-source MCP toolkit for offline manufacturing engineering workflows with FANUC LS and STEP/STP files
OpenFab MCP provides 4 tools with basic descriptions and minimal parameter documentation. Tool names follow verb_noun convention (step_analyze, fanuc_parse_ls, fanuc_lint_ls, fanuc_generate_ls_draft), which is good. However, parameter descriptions are sparse or missing entirely. Input schemas are visible but lack detail, most parameters have only type and description fields, with no enums, constraints, ranges, or validation guidance. Output schemas are not documented in the source. Error handling is minimal; no recovery guidance or actionable error messages visible. The server targets offline engineering workflows (safe domain), but lacks the structured output documentation and parameter constraints expected of production tools.
Generate an explicitly non-production FANUC LS offline draft from structured input.
Lint FANUC LS source offline and return structured diagnostics.
Parse FANUC LS source from exactly one local .ls path or LS text string.
Analyze a local STEP/STP file offline. No CAM, deployment, or robot control is performed.
Output schemas not documented. LLMs cannot plan downstream calls or extract required fields without knowing what each tool returns. step_analyze, fanuc_parse_ls, fanuc_lint_ls, and fanuc_generate_ls_draft all return dict[str, Any] with no schema specification visible.
Parameter descriptions are minimal or absent. fanuc_parse_ls and fanuc_lint_ls accept optional 'path' and 'text' parameters but do not document the mutual exclusivity constraint, expected formats, or error behavior when both/neither are provided. fanuc_generate_ls_draft accepts a 'draft' object with no schema or field documentation.
No input validation constraints or enums. step_analyze accepts a 'path' string with no guidance on file extensions (.step, .stp), path format, or size limits. fanuc_parse_ls and fanuc_lint_ls accept 'text' with no length or encoding constraints. LLMs will pass invalid inputs without guidance.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 49 | 2026-07-28+ | v2 |
Error handling not visible in tool definitions. No recovery guidance, error classification, or actionable messages documented. Agents cannot determine if errors are retryable, user-fixable, or fatal.
fanuc_generate_ls_draft marked as WRITE risk but no confirmation or dry-run pattern documented. Agents cannot preview output before committing. No idempotency guarantee stated.