Agent Knowledge MCP

Instructions

Implementation Reference

• src/elasticsearch/sub_servers/elasticsearch_document.py:79-123 (handler)

  The get_document tool handler: async function that uses Elasticsearch client to retrieve a document by index and doc_id. Includes input schema via Annotated[Field], JSON output formatting, and detailed error handling for connection issues, missing index, missing document, etc.
  @app.tool( description="Retrieve a specific document from Elasticsearch index by document ID", tags={"elasticsearch", "get", "document", "retrieve"} ) async def get_document( index: Annotated[str, Field(description="Name of the Elasticsearch index containing the document")], doc_id: Annotated[str, Field(description="Document ID to retrieve from the index")] ) -> str: """Retrieve a specific document from Elasticsearch index.""" try: es = get_es_client() result = es.get(index=index, id=doc_id) return f"✅ Document retrieved successfully:\n\n{json.dumps(result, indent=2, ensure_ascii=False)}" except Exception as e: # Provide detailed error messages for different types of Elasticsearch errors error_message = "❌ Failed to get document:\n\n" error_str = str(e).lower() if "connection" in error_str or "refused" in error_str: error_message += "🔌 **Connection Error**: Cannot connect to Elasticsearch server\n" error_message += f"📍 Check if Elasticsearch is running at the configured address\n" error_message += f"💡 Try: Use 'setup_elasticsearch' tool to start Elasticsearch\n\n" elif ( "not_found" in error_str or "not found" in error_str) or "index_not_found_exception" in error_str or "no such index" in error_str: if "index" in error_str or "index_not_found_exception" in error_str or "no such index" in error_str: error_message += f"📁 **Index Not Found**: Index '{index}' does not exist\n" error_message += f"📍 The target index has not been created yet\n" error_message += f"💡 **Suggestions for agents**:\n" error_message += f" 1. Use 'list_indices' tool to see all available indices\n" error_message += f" 2. Check which indices contain your target data\n" error_message += f" 3. Use the correct index name from the list\n" error_message += f" 4. If no suitable index exists, create one with 'create_index' tool\n\n" else: error_message += f"📄 **Document Not Found**: Document ID '{doc_id}' does not exist\n" error_message += f"📍 The requested document was not found in index '{index}'\n" error_message += f"💡 Try: Check document ID or use 'search' to find documents\n\n" else: error_message += f"⚠️ **Unknown Error**: {str(e)}\n\n" error_message += f"🔍 **Technical Details**: {str(e)}" return error_message
• src/elasticsearch/elasticsearch_server.py:27-48 (registration)

  Mounts the elasticsearch_document sub-server into the unified Elasticsearch server app, registering the get_document tool (along with index_document and delete_document).
  from .sub_servers.elasticsearch_document import app as document_app from .sub_servers.elasticsearch_index import app as index_app from .sub_servers.elasticsearch_search import app as search_app from .sub_servers.elasticsearch_batch import app as batch_app # Create unified FastMCP application app = FastMCP( name="AgentKnowledgeMCP-Elasticsearch", version="2.0.0", instructions="Unified Elasticsearch tools for comprehensive knowledge management via modular server mounting" ) # ================================ # SERVER MOUNTING - MODULAR ARCHITECTURE # ================================ print("🏗️ Mounting Elasticsearch sub-servers...") # Mount all sub-servers into unified interface app.mount(snapshots_app) # 3 tools: snapshot management app.mount(index_metadata_app) # 3 tools: metadata governance app.mount(document_app) # 3 tools: document operations
• src/main_server.py:19-76 (registration)

  Mounts the elasticsearch_server_app into the main FastMCP server, making get_document available at the top level.
  from src.elasticsearch.elasticsearch_server import app as elasticsearch_server_app from src.prompts.prompt_server import app as prompt_server_app # Import middleware from src.middleware.confirmation_middleware import ConfirmationMiddleware # Load configuration and initialize components CONFIG = load_config() init_security(CONFIG["security"]["allowed_base_directory"]) # Initialize confirmation manager confirmation_manager = initialize_confirmation_manager(CONFIG) print(f"✅ Confirmation system initialized (enabled: {CONFIG.get('confirmation', {}).get('enabled', True)})") # Auto-setup Elasticsearch if needed print("🔍 Checking Elasticsearch configuration...") config_path = Path(__file__).parent / "config.json" setup_result = auto_setup_elasticsearch(config_path, CONFIG) if setup_result["status"] == "setup_completed": # Reload config after setup CONFIG = load_config() print("✅ Elasticsearch auto-setup completed") elif setup_result["status"] == "already_configured": print("✅ Elasticsearch already configured") elif setup_result["status"] == "setup_failed": print(f"⚠️ Elasticsearch auto-setup failed: {setup_result.get('error', 'Unknown error')}") print("📝 You can manually setup using the 'setup_elasticsearch' tool") init_elasticsearch(CONFIG) # Create main FastMCP server app = FastMCP( name=CONFIG["server"]["name"], version=CONFIG["server"]["version"], instructions="🏗️ AgentKnowledgeMCP - Modern FastMCP server with modular composition architecture for knowledge management, Elasticsearch operations, file management, and system administration" ) # ================================ # MIDDLEWARE CONFIGURATION # ================================ print("🔒 Adding confirmation middleware...") # Add confirmation middleware to main server app.add_middleware(ConfirmationMiddleware()) print("✅ Confirmation middleware added successfully!") # ================================ # SERVER COMPOSITION - MOUNTING # ================================ print("🏗️ Mounting individual servers into main server...") # Mount Elasticsearch server with 'es' prefix # This provides: es_search, es_index_document, es_create_index, etc. app.mount(elasticsearch_server_app)
• src/elasticsearch/sub_servers/elasticsearch_document.py:84-85 (schema)

  Input schema for get_document tool: requires 'index' (str) and 'doc_id' (str) parameters with descriptions.
  index: Annotated[str, Field(description="Name of the Elasticsearch index containing the document")], doc_id: Annotated[str, Field(description="Document ID to retrieve from the index")]