Skip to main content
Glama
ergut

MCP server for LogSeq

by ergut

search

Search for content across LogSeq pages, blocks, and files to find specific information within your knowledge base.

Instructions

Search for content across LogSeq pages, blocks, and files

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query text
limitNoMaximum number of results to return
include_blocksNoInclude block content results
include_pagesNoInclude page name results
include_filesNoInclude file name results

Implementation Reference

  • The run_tool method implements the core logic of the 'search' tool: it validates input arguments, calls the LogSeq API's search_content method, processes and formats the results into categorized sections (blocks, snippets, pages, files), handles pagination info, and returns formatted TextContent.
    def run_tool(self, args: dict) -> list[TextContent]:
        """Execute search and format results."""
        logger.info(f"Searching with args: {args}")
        
        if "query" not in args:
            raise RuntimeError("query argument required")
    
        query = args["query"]
        limit = args.get("limit", 20)
        include_blocks = args.get("include_blocks", True)
        include_pages = args.get("include_pages", True)
        include_files = args.get("include_files", False)
    
        try:
            # Prepare search options
            search_options = {"limit": limit}
            
            api = logseq.LogSeq(api_key=api_key)
            result = api.search_content(query, search_options)
            
            if not result:
                return [TextContent(
                    type="text",
                    text=f"No search results found for '{query}'"
                )]
    
            # Format results
            content_parts = []
            content_parts.append(f"# Search Results for '{query}'\n")
            
            # Block results
            if include_blocks and result.get("blocks"):
                blocks = result["blocks"]
                content_parts.append(f"## 📄 Content Blocks ({len(blocks)} found)")
                for i, block in enumerate(blocks[:limit]):
                    # LogSeq returns blocks with 'block/content' key
                    content = block.get("block/content", "").strip()
                    if content:
                        # Truncate long content
                        if len(content) > 150:
                            content = content[:150] + "..."
                        content_parts.append(f"{i+1}. {content}")
                content_parts.append("")
    
            # Page snippet results  
            if include_blocks and result.get("pages-content"):
                snippets = result["pages-content"]
                content_parts.append(f"## 📝 Page Snippets ({len(snippets)} found)")
                for i, snippet in enumerate(snippets[:limit]):
                    # LogSeq returns snippets with 'block/snippet' key  
                    snippet_text = snippet.get("block/snippet", "").strip()
                    if snippet_text:
                        # Clean up snippet text
                        snippet_text = snippet_text.replace("$pfts_2lqh>$", "").replace("$<pfts_2lqh$", "")
                        if len(snippet_text) > 200:
                            snippet_text = snippet_text[:200] + "..."
                        content_parts.append(f"{i+1}. {snippet_text}")
                content_parts.append("")
    
            # Page name results
            if include_pages and result.get("pages"):
                pages = result["pages"]
                content_parts.append(f"## 📑 Matching Pages ({len(pages)} found)")
                for page in pages:
                    content_parts.append(f"- {page}")
                content_parts.append("")
    
            # File results
            if include_files and result.get("files"):
                files = result["files"]
                content_parts.append(f"## 📁 Matching Files ({len(files)} found)")
                for file_path in files:
                    content_parts.append(f"- {file_path}")
                content_parts.append("")
    
            # Pagination info
            if result.get("has-more?"):
                content_parts.append("📌 *More results available - increase limit to see more*")
    
            # Summary
            total_results = len(result.get("blocks", [])) + len(result.get("pages", [])) + len(result.get("files", []))
            content_parts.append(f"\n**Total results found: {total_results}**")
    
            response_text = "\n".join(content_parts)
            
            return [TextContent(type="text", text=response_text)]
            
        except Exception as e:
            logger.error(f"Failed to search: {str(e)}")
            return [TextContent(
                type="text",
                text=f"❌ Search failed: {str(e)}"
            )]
  • The get_tool_description method returns the Tool object defining the schema for the 'search' tool, including input parameters: query (required), limit, include_blocks, include_pages, include_files.
    def get_tool_description(self):
        return Tool(
            name=self.name,
            description="Search for content across LogSeq pages, blocks, and files",
            inputSchema={
                "type": "object",
                "properties": {
                    "query": {
                        "type": "string",
                        "description": "Search query text"
                    },
                    "limit": {
                        "type": "integer",
                        "description": "Maximum number of results to return",
                        "default": 20
                    },
                    "include_blocks": {
                        "type": "boolean",
                        "description": "Include block content results",
                        "default": True
                    },
                    "include_pages": {
                        "type": "boolean", 
                        "description": "Include page name results",
                        "default": True
                    },
                    "include_files": {
                        "type": "boolean",
                        "description": "Include file name results", 
                        "default": False
                    }
                },
                "required": ["query"]
            }
        )
  • The registration block where all tool handlers are added to the tool_handlers dictionary, specifically including add_tool_handler(tools.SearchToolHandler()) on line 80.
    logger.info("Registering tool handlers...")
    add_tool_handler(tools.CreatePageToolHandler())
    add_tool_handler(tools.ListPagesToolHandler())
    add_tool_handler(tools.GetPageContentToolHandler())
    add_tool_handler(tools.DeletePageToolHandler())
    add_tool_handler(tools.UpdatePageToolHandler())
    add_tool_handler(tools.SearchToolHandler())
    logger.info("Tool handlers registration complete")

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/ergut/mcp-logseq-server'

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