TwinCAT Validator MCP Server

Validate a single TwinCAT file.

Args: file_path: Path to TwinCAT file validation_level: "all", "critical", or "style" profile: Output profile - "full" (verbose, default) or "llm_strict" (minimal) intent_profile: Programming paradigm intent — "auto" (default), "procedural", or "oop". Controls which check families run: - "procedural": OOP checks are skipped. - "oop": Full OOP check family is enforced. - "auto": Resolved from file content (EXTENDS/IMPLEMENTS → oop, else procedural).

Returns: JSON string with validation results.

Full profile includes: validation_status, checks array, issues with Phase 3
enrichment, metrics, timing.

LLM strict profile includes only: file_path, safe_to_import, safe_to_compile,
blocking_count, blockers (unfixable errors).

Quick validation check for TwinCAT import readiness.

Args: file_path: Path to TwinCAT file

Run specific validation checks on a TwinCAT file.

Args: file_path: Path to TwinCAT file check_names: List of check IDs to run

Get high-level file quality summary with health score.

Args: file_path: Path to TwinCAT file

Generate prioritized fix recommendations from validation results.

Args: validation_result: JSON string from validate_file()

Automatically fix common TwinCAT XML issues.

Args: file_path: Path to TwinCAT file create_backup: Create backup before fixing fixes_to_apply: List of fix IDs, or None for all profile: "full" (default) verbose response, "llm_strict" minimal response format_profile: "default" or "twincat_canonical" formatting pass strict_contract: If True, fail closed on generation-contract violations create_implicit_files: If True, auto-create missing implicit dependency files (currently interface .TcIO files for IMPLEMENTS I_* clauses) orchestration_hints: If True, include next_action/terminal/no_change hints and content fingerprints for loop prevention in weak agents. intent_profile: Programming paradigm intent — "auto" (default), "procedural", or "oop". Controls which check families are used in post-fix validation.

Generate canonical deterministic TwinCAT XML skeleton for a file type.

Args: file_type: .TcPOU, .TcDUT, .TcGVL, or .TcIO (with or without leading dot) subtype: For .TcPOU only: function_block, function, or program

Promote inline METHOD blocks from main ST to XML elements.

Args: file_path: Path to .TcPOU file create_backup: Create .bak backup when content changes

Validate multiple TwinCAT files matching glob patterns.

Args: file_patterns: Glob patterns (e.g., ["*.TcPOU"]) directory_path: Base directory validation_level: "all", "critical", or "style" intent_profile: Programming paradigm intent — "auto" (default), "procedural", or "oop". With "auto", the matched .TcPOU files are scanned for EXTENDS/ IMPLEMENTS; if any are found the batch resolves to "oop", otherwise "procedural". ctx: FastMCP context for per-file progress notifications (injected automatically)

Automatically fix multiple TwinCAT files matching glob patterns.

Args: file_patterns: Glob patterns (e.g., ["*.TcPOU"]) directory_path: Base directory create_backup: Create backup files before fixing profile: Response profile passed to per-file autofix (default: llm_strict) format_profile: Formatting profile for per-file autofix strict_contract: Enforce generation contract fail-closed in per-file autofix create_implicit_files: Auto-create missing interface/DUT dependencies orchestration_hints: Include loop-guard hints in per-file responses intent_profile: Programming paradigm intent — "auto" (default), "procedural", or "oop". With "auto", each file's content is inspected individually for EXTENDS/IMPLEMENTS, so OOP files receive full OOP checks even in mixed batches. ctx: FastMCP context for per-file progress notifications (injected automatically)

Run enforced deterministic single-file TwinCAT workflow.

Steps:

1. validate_file (pre-check)

2. autofix_file (strict pipeline)

3. validate_file (post-check)

4. suggest_fixes (only if still unsafe)

Args: file_path: Path to the TwinCAT file to process. create_backup: Create a backup before applying fixes. validation_level: "all", "critical", or "style". enforcement_mode: Policy enforcement mode ("strict" or "compat"). include_knowledge_hints: Include recommended_check_ids from blockers. intent_profile: Programming paradigm intent — "auto" (default), "procedural", or "oop". Controls which check families run: - "procedural": OOP checks are skipped (safe for plain FUNCTION_BLOCK/PROGRAM). - "oop": Full OOP check family is enforced. - "auto": Resolved from file content (EXTENDS/IMPLEMENTS → oop, else procedural).

Run enforced deterministic batch TwinCAT workflow.

Steps:

1. validate_batch (pre-check)

2. autofix_batch (strict pipeline)

3. validate_batch (post-check)

Args: file_patterns: Glob patterns (e.g., ["*.TcPOU"]) directory_path: Base directory create_backup: Create backup files before fixing validation_level: "all", "critical", or "style" enforcement_mode: Policy enforcement mode ("strict" or "compat") response_mode: "summary" (minimal, default), "compact" (no pre/post blobs), or "full" (all detail sections included). include_sections: In summary mode only — optional list of heavy sections to add. Supported: "blockers", "issues", "pre_validation", "autofix", "post_validation", "effective_oop_policy", "meta_detailed". Unknown names are ignored with a warning in the response. Has no effect in compact or full mode. include_knowledge_hints: Include recommended_check_ids from blockers (when not done). intent_profile: Programming paradigm intent — "auto" (default), "procedural", or "oop". Controls which check families run: - "procedural": OOP checks are skipped. - "oop": Full OOP check family is enforced. - "auto": Scans matched .TcPOU declarations for EXTENDS/IMPLEMENTS; resolves to "oop" if any are found, otherwise "procedural".

Run strict batch orchestration twice and report per-file idempotence stability.

Args: file_patterns: Glob patterns (e.g., ["*.TcPOU"]) directory_path: Base directory create_backup: Create backup files before fixing validation_level: "all", "critical", or "style" enforcement_mode: Policy enforcement mode ("strict" or "compat") response_mode: "summary" (minimal, default), "compact", or "full". include_sections: In summary mode only — optional heavy sections to include. Supported: "blockers", "pre_validation", "autofix", "post_validation", "effective_oop_policy", "meta_detailed". Unknown names ignored with a warning in the response. Has no effect in compact or full mode.

Get effective OOP validation policy for a file or directory target.

Args: target_path: Optional path to a file or directory. If omitted, uses current working directory defaults.

Lint nearest .twincat-validator.json policy keys/types and return normalized policy.

Get curated knowledge base entries and OOP policy scoped by workflow stage.

Stages:

• pre_generation: Returns high-priority non-fixable checks the LLM must get right when generating TwinCAT XML from scratch.

• troubleshooting: Returns KB entries for specific check_ids (typically extracted from blocker lists after orchestration).

Args: stage: Workflow stage ("pre_generation" or "troubleshooting"). check_ids: Explicit check IDs (required for troubleshooting, ignored for pre_generation). target_path: Optional file/dir path for OOP policy resolution. max_entries: Maximum KB entries to return (default 10). include_examples: Include correct_examples and common_mistakes arrays (default True). Set False to save tokens. enforcement_mode: Policy enforcement mode ("strict" or "compat"). intent_profile: Programming paradigm intent — "oop", "procedural", or "auto". In pre_generation stage: - omitted: defaults to "oop" (backward compatible behavior). - "oop": Core + OOP check guidance is returned. - "procedural": Only core (non-OOP) check guidance is returned. - "auto": No file content is available at pre-generation time, so resolves to "procedural". Use "oop" or "procedural" explicitly for predictability. In troubleshooting stage: - explicit value is required (workflow guardrail). - value has no routing effect (check_ids drive selection).

Returns: JSON with effective_oop_policy, curated entries[], missing_check_ids[], intent metadata, truncation info, and meta envelope.