obsidian_complex_search
Search Obsidian documents using JsonLogic queries with glob and regex operators to find files by path, content, tags, and patterns.
Instructions
Complex search for documents using a JsonLogic query. Supports standard JsonLogic operators plus 'glob' and 'regexp' for pattern matching. Results must be non-falsy.
Use this tool when you want to do a complex search, e.g. for all documents with certain tags etc.
ALWAYS follow query syntax in examples.
Examples
1. Match all markdown files
{"glob": ["*.md", {"var": "path"}]}
2. Match all markdown files with 1221 substring inside them
{
"and": [
{ "glob": ["*.md", {"var": "path"}] },
{ "regexp": [".*1221.*", {"var": "content"}] }
]
}
3. Match all markdown files in Work folder containing name Keaton
{
"and": [
{ "glob": ["*.md", {"var": "path"}] },
{ "regexp": [".*Work.*", {"var": "path"}] },
{ "regexp": ["Keaton", {"var": "content"}] }
]
}
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | JsonLogic query object. ALWAYS follow query syntax in examples. Example 1: {"glob": ["*.md", {"var": "path"}]} matches all markdown files Example 2: {"and": [{"glob": ["*.md", {"var": "path"}]}, {"regexp": [".*1221.*", {"var": "content"}]}]} matches all markdown files with 1221 substring inside them Example 3: {"and": [{"glob": ["*.md", {"var": "path"}]}, {"regexp": [".*Work.*", {"var": "path"}]}, {"regexp": ["Keaton", {"var": "content"}]}]} matches all markdown files in Work folder containing name Keaton |
Implementation Reference
- src/mcp_obsidian/tools.py:373-436 (handler)The ComplexSearchToolHandler class defines the tool handler, including __init__ setting the tool name, get_tool_description providing schema and description, and run_tool executing the search via Obsidian API.class ComplexSearchToolHandler(ToolHandler): def __init__(self): super().__init__("obsidian_complex_search") def get_tool_description(self): return Tool( name=self.name, description="""Complex search for documents using a JsonLogic query. Supports standard JsonLogic operators plus 'glob' and 'regexp' for pattern matching. Results must be non-falsy. Use this tool when you want to do a complex search, e.g. for all documents with certain tags etc. ALWAYS follow query syntax in examples. Examples 1. Match all markdown files {"glob": ["*.md", {"var": "path"}]} 2. Match all markdown files with 1221 substring inside them { "and": [ { "glob": ["*.md", {"var": "path"}] }, { "regexp": [".*1221.*", {"var": "content"}] } ] } 3. Match all markdown files in Work folder containing name Keaton { "and": [ { "glob": ["*.md", {"var": "path"}] }, { "regexp": [".*Work.*", {"var": "path"}] }, { "regexp": ["Keaton", {"var": "content"}] } ] } """, inputSchema={ "type": "object", "properties": { "query": { "type": "object", "description": "JsonLogic query object. ALWAYS follow query syntax in examples. \ Example 1: {\"glob\": [\"*.md\", {\"var\": \"path\"}]} matches all markdown files \ Example 2: {\"and\": [{\"glob\": [\"*.md\", {\"var\": \"path\"}]}, {\"regexp\": [\".*1221.*\", {\"var\": \"content\"}]}]} matches all markdown files with 1221 substring inside them \ Example 3: {\"and\": [{\"glob\": [\"*.md\", {\"var\": \"path\"}]}, {\"regexp\": [\".*Work.*\", {\"var\": \"path\"}]}, {\"regexp\": [\"Keaton\", {\"var\": \"content\"}]}]} matches all markdown files in Work folder containing name Keaton \ " } }, "required": ["query"] } ) def run_tool(self, args: dict) -> Sequence[TextContent | ImageContent | EmbeddedResource]: if "query" not in args: raise RuntimeError("query argument missing in arguments") api = obsidian.Obsidian(api_key=api_key, host=obsidian_host) results = api.search_json(args.get("query", "")) return [ TextContent( type="text", text=json.dumps(results, indent=2) ) ]
- src/mcp_obsidian/server.py:52-52 (registration)Registers the ComplexSearchToolHandler instance in the tool_handlers dictionary via add_tool_handler.add_tool_handler(tools.ComplexSearchToolHandler())
- src/mcp_obsidian/obsidian.py:183-195 (helper)The search_json method in Obsidian class performs the actual JSON logic search by posting the query to the Obsidian API endpoint /search/.def search_json(self, query: dict) -> Any: url = f"{self.get_base_url()}/search/" headers = self._get_headers() | { 'Content-Type': 'application/vnd.olrapi.jsonlogic+json' } def call_fn(): response = requests.post(url, headers=headers, json=query, verify=self.verify_ssl, timeout=self.timeout) response.raise_for_status() return response.json() return self._safe_call(call_fn)