Skip to main content
Glama
MarkusPfundstein

MCP server for Obsidian

obsidian_simple_search

Search across all Obsidian vault files for documents containing specific text queries, returning relevant matches with context.

Instructions

Simple search for documents matching a specified text query across all files in the vault. Use this tool when you want to do a simple text search

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesText to a simple search for in the vault.
context_lengthNoHow much context to return around the matching string (default: 100)

Implementation Reference

  • The `run_tool` method in `SearchToolHandler` class executes the obsidian_simple_search tool: validates input, calls Obsidian API search, formats results with context and match positions, and returns JSON-formatted TextContent.
    def run_tool(self, args: dict) -> Sequence[TextContent | ImageContent | EmbeddedResource]:
        if "query" not in args:
            raise RuntimeError("query argument missing in arguments")
    
        context_length = args.get("context_length", 100)
        
        api = obsidian.Obsidian(api_key=api_key, host=obsidian_host)
        results = api.search(args["query"], context_length)
        
        formatted_results = []
        for result in results:
            formatted_matches = []
            for match in result.get('matches', []):
                context = match.get('context', '')
                match_pos = match.get('match', {})
                start = match_pos.get('start', 0)
                end = match_pos.get('end', 0)
                
                formatted_matches.append({
                    'context': context,
                    'match_position': {'start': start, 'end': end}
                })
                
            formatted_results.append({
                'filename': result.get('filename', ''),
                'score': result.get('score', 0),
                'matches': formatted_matches
            })
    
        return [
            TextContent(
                type="text",
                text=json.dumps(formatted_results, indent=2)
            )
        ]
  • The `get_tool_description` method defines the tool schema including name, description, and inputSchema for query (required string) and optional context_length (integer, default 100).
    def get_tool_description(self):
        return Tool(
            name=self.name,
            description="""Simple search for documents matching a specified text query across all files in the vault. 
            Use this tool when you want to do a simple text search""",
            inputSchema={
                "type": "object",
                "properties": {
                    "query": {
                        "type": "string",
                        "description": "Text to a simple search for in the vault."
                    },
                    "context_length": {
                        "type": "integer",
                        "description": "How much context to return around the matching string (default: 100)",
                        "default": 100
                    }
                },
                "required": ["query"]
            }
        )
  • Registers the SearchToolHandler instance by adding it to the tool_handlers dictionary via add_tool_handler.
    add_tool_handler(tools.SearchToolHandler())

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/MarkusPfundstein/mcp-obsidian'

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