Dedalus MCP Documentation Server

Instructions

Implementation Reference

• src/main.py:396-430 (handler)

  The handler function for the 'index_docs' MCP tool. It clears caches if rebuild=True, then iterates over all .md files in DOCS_DIR, calls get_doc_metadata on each, accumulates stats on files indexed and total size, catches errors, and returns indexing statistics. Registered via the @mcp.tool() decorator which also defines the schema from the signature and docstring.
  @mcp.tool() def index_docs(rebuild: bool = False) -> Dict[str, Any]: """ Index or re-index all documentation for improved search Args: rebuild: Whether to rebuild the entire index from scratch Returns: Indexing statistics """ if rebuild: METADATA_CACHE.clear() EMBEDDINGS_CACHE.clear() stats = { 'files_indexed': 0, 'total_size': 0, 'errors': [], 'timestamp': datetime.now().isoformat(), } for file_path in DOCS_DIR.rglob('*.md'): try: if file_path.is_file(): metadata = get_doc_metadata(file_path) stats['files_indexed'] += 1 stats['total_size'] += metadata['size'] # Here you would generate embeddings for semantic search # EMBEDDINGS_CACHE[file_path] = generate_embeddings(content) except Exception as e: stats['errors'].append({'file': str(file_path), 'error': str(e)}) return stats
• src/main.py:125-150 (helper)

  Helper function used by index_docs (and other tools) to extract metadata like title, path, modified time, size, hash from markdown files, caching the results in METADATA_CACHE. Attempts to parse title from first H1 heading.
  def get_doc_metadata(file_path: Path) -> Dict[str, Any]: """Extract metadata from markdown files""" if file_path in METADATA_CACHE: return METADATA_CACHE[file_path] metadata = { 'title': file_path.stem.replace('-', ' ').title(), 'path': str(file_path.relative_to(DOCS_DIR)), 'modified': datetime.fromtimestamp(file_path.stat().st_mtime).isoformat(), 'size': file_path.stat().st_size, 'hash': hashlib.md5(file_path.read_bytes()).hexdigest(), } # Try to extract title from first # heading try: content = file_path.read_text() lines = content.split('\n') for line in lines[:10]: # Check first 10 lines if line.startswith('# '): metadata['title'] = line[2:].strip() break except (OSError, UnicodeDecodeError): pass METADATA_CACHE[file_path] = metadata return metadata