Chuyển tới nội dung RAG Anything MCP Server
An MCP (Model Context Protocol) server that provides comprehensive RAG (Retrieval-Augmented Generation) capabilities for processing and querying directories of documents using the raganything library with full multimodal support.
Features
End-to-End Document Processing : Complete document parsing with multimodal content extraction
An MCP server for rag-anything (A multi-modal RAG system)
Cắm mọi công cụ vào mọi agent. Thư mục MCP cho người không viết server.
Sản phẩm
Thư mục
Nhà phát triển
Công ty
2026-10-28
Sao 38
Công cụ —
Thời gian hoạt động —
Multimodal RAG : Support for images, tables, equations, and text processing
Batch Processing : Process entire directories with multiple file types
Advanced Querying : Both pure text and multimodal-enhanced queries
Multiple Query Modes : hybrid, local, global, naive, mix, and bypass modes
Vision Processing : Advanced image analysis using GPT-4V
Persistent Storage : RAG instances maintained per directory for efficient querying
Available Tools
process_directoryProcess all files in a directory for comprehensive RAG indexing with multimodal support.
directory_path: Path to the directory containing files to process
api_key: OpenAI API key for LLM and embedding functions
working_dir: Custom working directory for RAG storage
base_url: OpenAI API base URL (for custom endpoints)
file_extensions: List of file extensions to process (default: ['.pdf', '.docx', '.pptx', '.txt', '.md'])
recursive: Process subdirectories (default: True)
enable_image_processing: Enable image analysis (default: True)
enable_table_processing: Enable table extraction (default: True)
enable_equation_processing: Enable equation processing (default: True)
max_workers: Concurrent processing workers (default: 4)
process_single_documentProcess a single document with full multimodal analysis.
file_path: Path to the document to process
api_key: OpenAI API key
working_dir: Custom working directory for RAG storage
base_url: OpenAI API base URL
output_dir: Output directory for parsed content
parse_method: Document parsing method (default: "auto")
enable_image_processing: Enable image analysis (default: True)
enable_table_processing: Enable table extraction (default: True)
enable_equation_processing: Enable equation processing (default: True)
query_directoryPure text query against processed documents using LightRAG.
directory_path: Path to the processed directory
query: The question to ask about the documents
mode: Query mode - "hybrid", "local", "global", "naive", "mix", or "bypass" (default: "hybrid")
query_with_multimodal_contentEnhanced query with additional multimodal content (tables, equations, etc.).
directory_path: Path to the processed directory
query: The question to ask
multimodal_content: List of multimodal content dictionaries
mode: Query mode (default: "hybrid")
Example multimodal_content:
[
{
"type": "table",
"table_data": "Method,Accuracy\\nRAGAnything,95.2%\\nBaseline,87.3%",
"table_caption": "Performance comparison"
},
{
"type": "equation",
"latex": "P(d|q) = \\frac{P(q|d) \\cdot P(d)}{P(q)}",
"equation_caption": "Document relevance probability"
}
]
list_processed_directoriesList all directories that have been processed and are available for querying.
get_rag_infoGet detailed information about the RAG configuration and status for a directory.
Usage Examples
1. Basic Directory Processing process_directory(
directory_path="/path/to/documents",
api_key="your-openai-api-key"
)
2. Advanced Directory Processing process_directory(
directory_path="/path/to/research_papers",
api_key="your-openai-api-key",
file_extensions=[".pdf", ".docx"],
enable_image_processing=true,
enable_table_processing=true,
max_workers=6
)
3. Pure Text Query query_directory(
directory_path="/path/to/documents",
query="What are the main findings in these research papers?",
mode="hybrid"
)
4. Multimodal Query with Table Data query_with_multimodal_content(
directory_path="/path/to/documents",
query="Compare these results with the document findings",
multimodal_content=[{
"type": "table",
"table_data": "Method,Accuracy,Speed\\nRAGAnything,95.2%,120ms\\nBaseline,87.3%,180ms",
"table_caption": "Performance comparison"
}],
mode="hybrid"
)
5. Single Document Processing process_single_document(
file_path="/path/to/important_paper.pdf",
api_key="your-openai-api-key",
enable_image_processing=true
)
Setup Requirements
1. Environment Variables export OPENAI_API_KEY="your-openai-api-key-here"
2. Install Dependencies
3. Run the MCP Server
Query Modes Explained
hybrid : Combines local and global search (recommended for most use cases)
local : Focuses on local context and entity relationships
global : Provides broader, document-level insights and summaries
naive : Simple keyword-based search without graph reasoning
mix : Combines multiple approaches for comprehensive results
bypass : Direct access without RAG processing
Multimodal Content Types The server supports processing and querying with:
Images : Automatic caption generation and visual analysis
Tables : Structure extraction and content analysis
Equations : LaTeX parsing and mathematical reasoning
Charts/Graphs : Visual data interpretation
Mixed Content : Combined analysis of multiple content types
API Configuration The server uses OpenAI's APIs by default:
LLM : GPT-4o-mini for text processing
Vision : GPT-4o for image analysis
Embeddings : text-embedding-3-large (3072 dimensions)
You can customize the base_url parameter to use:
Azure OpenAI
OpenAI-compatible APIs
Custom model endpoints
File Support Supported file formats include:
PDF documents
Microsoft Word (.docx)
PowerPoint presentations (.pptx)
Text files (.txt)
Markdown files (.md)
And more via the raganything library
Performance Notes
Concurrent Processing : Use max_workers to control parallel document processing
Memory Usage : Large documents with many images may require significant memory
API Costs : Vision processing (GPT-4o) is more expensive than text processing
Storage : Processed data is stored locally for efficient re-querying
Điểm thư mục 16/100 Đã liệt kê 10 trên 10
Có trong MCP Registry chính thức 0 trên 18
Đã được người bảo trì nhận 0 trên 8
Trả về danh sách công cụ 0 trên 12
Sao GitHub 10 trên 16
Lượt tải hằng tuần 0 trên 10
Graphify Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, e Understand Anything Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, Sequential Thinking Step-by-step problem solving for agents: break a problem into thoughts, revise them and branch. The reference server from the Model Context Protocol project. Memory Persistent memory for agents as a local knowledge graph of entities, relations and observations. The reference server from the Model Context Protocol project. Ruflo 🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, feder Codegraph Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, CoPilot, and Hermes Agent — fewer tokens, fewer tool calls, 100% loca Codebase Memory Local code intelligence for developers and AI agents. Connect code, docs and infrastructure in a persistent graph, with CBM Lens, MCP tools, agent integrations and change-aware test selection. Codebase Memory Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens. Codebase Memory Local code intelligence for developers and AI agents. Connect code, docs and infrastructure in a persistent graph, with CBM Lens, MCP tools, agent integrations and change-aware test selection. Context Mode Free, local plugin that keeps tool output out of your coding agent's context window. Sandbox and SQLite FTS5 search, 99% fewer bytes in context. Works with Claude Code, Codex, Pi, OMP, OpenCode, Gemin MaxKB 🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。 Xerj AI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory a Máy chủ MCP Knowledge and memory Máy chủ MCP Knowledge and memory tốt nhất
Chưa có danh sách công cụ. Máy chủ từ xa sẽ có danh sách sau lần kiểm tra tình trạng đầu tiên.
Câu hỏi thường gặp
Câu hỏi Làm thế nào để cài đặt Rag Anything? Sao chép cấu hình stdio cho Cursor, Claude Desktop, Claude Code hoặc VS Code trên trang này. Cấu hình dùng bản cài đặt của nhà phát hành, không phải proxy của PlugMCP.
Rag Anything có cần khóa API không? Bản ghi này không liệt kê biến môi trường bắt buộc nào.
Rag Anything dùng giao thức truyền tải nào? Rag Anything chạy cục bộ qua stdio.
Rag Anything được kiểm tra lần cuối khi nào? Kiểm tra lần cuối: 2026-10-28. An MCP server for rag-anything (A multi-modal RAG system)
Sẵn sàng cho thoại 0 trên 3
Không thấy trong ba ngày -8