MCPVault

query

MCP tool from Rag Anything MCP by jesse-merhi

The question to ask about the documents

How to use it

query is exposed by the Rag Anything MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the query tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

FULL RAG ANYTHING MCP LISTING

Other tools in Rag Anything MCP (20)

base_url

OpenAI API base URL (for custom endpoints)

directory_path

Path to the directory containing files to process

enable_equation_processing

Enable equation processing (default: True)

enable_image_processing

Enable image analysis (default: True)

enable_table_processing

Enable table extraction (default: True)

file_extensions

List of file extensions to process (default: ['.pdf', '.docx', '.pptx', '.txt', '.md'])

file_path

Path to the document to process

get_rag_info

Get detailed information about the RAG configuration and status for a directory.

list_processed_directories

List all directories that have been processed and are available for querying.

max_workers

Concurrent processing workers (default: 4)

mode

Query mode - "hybrid", "local", "global", "naive", "mix", or "bypass" (default: "hybrid")

multimodal_content

List of multimodal content dictionaries

output_dir

Output directory for parsed content

parse_method

Document parsing method (default: "auto")

process_directory

Process all files in a directory for comprehensive RAG indexing with multimodal support.

process_single_document

Process a single document with full multimodal analysis.

query_directory

Pure text query against processed documents using LightRAG.

query_with_multimodal_content

Enhanced query with additional multimodal content (tables, equations, etc.).

recursive

Process subdirectories (default: True)

working_dir

Custom working directory for RAG storage