Skip to main content
Glama
cwente25

Knowledge Base MCP Server

by cwente25

list_notes

Retrieve notes from your knowledge base, with optional filtering by category or tag to organize information.

Instructions

List all notes, optionally filtered by category path or tag

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
category_pathNoOptional category path filter (e.g., 'work/clients')
tagNoOptional tag filter
recursiveNoIf true, list notes in subcategories too (default: true)

Implementation Reference

  • MCP tool handler function for list_notes. Processes input arguments, retrieves notes from storage, groups them by category, and returns a formatted text list.
    async def handle_list_notes(arguments: dict) -> list[TextContent]:
        """Handle list_notes tool call."""
        category_path = arguments.get("category_path")
        tag = arguments.get("tag")
        recursive = arguments.get("recursive", True)
    
        # Get notes
        notes = storage.list_notes(
            category_path=category_path,
            tag=tag,
            recursive=recursive
        )
    
        if not notes:
            return [TextContent(type="text", text="No notes found.")]
    
        # Group by category
        by_category = {}
        for note in notes:
            cat = note.category or 'root'
            if cat not in by_category:
                by_category[cat] = []
            by_category[cat].append(note)
    
        # Format output
        output_lines = []
    
        if category_path:
            recursive_str = " (including subcategories)" if recursive else " (non-recursive)"
            output_lines.append(f"Notes in {category_path}/{recursive_str} ({len(notes)} total):\n")
        else:
            output_lines.append(f"All notes ({len(notes)} total):\n")
    
        for cat in sorted(by_category.keys()):
            cat_notes = by_category[cat]
            output_lines.append(f"\n{cat}/ ({len(cat_notes)} notes):")
    
            for note in sorted(cat_notes, key=lambda n: n.title):
                tags_str = ', '.join(note.frontmatter.tags) if note.frontmatter.tags else 'no tags'
                output_lines.append(f"  - {note.title} [{tags_str}]")
    
        return [TextContent(type="text", text="\n".join(output_lines))]
  • Registration of the list_notes tool in the MCP server's list_tools() method, defining its name, description, and input schema.
        name="list_notes",
        description="List all notes, optionally filtered by category path or tag",
        inputSchema={
            "type": "object",
            "properties": {
                "category_path": {
                    "type": "string",
                    "description": "Optional category path filter (e.g., 'work/clients')",
                },
                "tag": {
                    "type": "string",
                    "description": "Optional tag filter",
                },
                "recursive": {
                    "type": "boolean",
                    "description": "If true, list notes in subcategories too (default: true)",
                    "default": True,
                },
            },
        },
    ),
  • Input schema/JSON Schema for the list_notes tool defining parameters: category_path, tag, recursive.
    inputSchema={
        "type": "object",
        "properties": {
            "category_path": {
                "type": "string",
                "description": "Optional category path filter (e.g., 'work/clients')",
            },
            "tag": {
                "type": "string",
                "description": "Optional tag filter",
            },
            "recursive": {
                "type": "boolean",
                "description": "If true, list notes in subcategories too (default: true)",
                "default": True,
            },
        },
    },
  • Helper method in KnowledgeBaseStorage that implements the core listing logic: scans directories for .md files recursively or not, parses each into Note objects, filters by tag, skips invalid files.
    def list_notes(
        self,
        category_path: Optional[str] = None,
        tag: Optional[str] = None,
        recursive: bool = True
    ) -> list[Note]:
        """
        List all notes, optionally filtered by category path or tag.
    
        Args:
            category_path: Optional category path filter (e.g., "work/clients")
            tag: Optional tag filter
            recursive: If True, include notes from subcategories (default: True)
    
        Returns:
            List of Note objects
        """
        notes = []
    
        # Determine which path to search
        if category_path:
            normalized = normalize_path(category_path)
            search_path = self._get_category_path(normalized)
            if not search_path.exists():
                return []
        else:
            search_path = self.base_path
    
        # Find all markdown files
        if recursive:
            pattern = "**/*.md"
        else:
            pattern = "*.md"
    
        for file_path in search_path.glob(pattern):
            # Skip backup and temp files
            if file_path.suffix in ('.backup', '.tmp', '.deleted'):
                continue
    
            try:
                note = self._parse_note_file(file_path)
    
                # Apply tag filter if specified
                if tag and tag.lower() not in [t.lower() for t in note.frontmatter.tags]:
                    continue
    
                notes.append(note)
    
            except StorageError:
                # Skip files that can't be parsed
                continue
    
        return notes

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cwente25/KnowledgeBaseMCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server