RAG-Anything MCP Server
by serkanyasr
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KG_PARSER | No | Document parser: mineru, docling | mineru |
| LOG_LEVEL | No | Application log level: DEBUG, INFO, WARNING, ERROR, CRITICAL | INFO |
| NEO4J_URI | No | Neo4j URI | bolt://localhost:7687 |
| LOG_FORMAT | No | Application log format: json, text | json |
| NEO4J_USER | No | Neo4j username | neo4j |
| RAG_DB_HOST | No | PostgreSQL host for RAG | localhost |
| RAG_DB_NAME | No | PostgreSQL database name | rag_anythink |
| RAG_DB_PORT | No | PostgreSQL port | 5432 |
| RAG_DB_USER | No | PostgreSQL user | postgres |
| RAG_MCP_LOG | No | MCP log level | info |
| KG_LLM_MODEL | No | LLM model for knowledge graph operations | gpt-4o-mini |
| KG_WORKSPACE | No | Workspace name | production |
| RAG_MCP_HOST | No | MCP server host | localhost |
| RAG_MCP_NAME | No | MCP server name | rag-anything-mcp |
| RAG_MCP_PORT | No | MCP server port | 8055 |
| KG_WORKING_DIR | No | Working directory for RAG output | ./rag_output |
| NEO4J_PASSWORD | No | Neo4j password | your_neo4j_password |
| OPENAI_API_KEY | Yes | OpenAI API key (required) | |
| KG_DEFAULT_MODE | No | Default query mode (naive, local, global, hybrid, mix, bypass) | hybrid |
| KG_ENABLE_IMAGE | No | Enable image extraction from PDFs | true |
| KG_ENABLE_TABLE | No | Enable table extraction from PDFs | true |
| KG_PARSE_METHOD | No | Parse method: auto, ocr, txt | auto |
| KG_VISION_MODEL | No | Vision model for multimodal processing | gpt-4o |
| RAG_DB_PASSWORD | No | PostgreSQL password | your_postgres_password |
| RAG_MCP_VERSION | No | MCP server version | 1.0.0 |
| KG_EMBEDDING_DIM | No | Embedding dimension | 3072 |
| KG_CONTEXT_WINDOW | No | Context window for LLM (pages before/after) | 1 |
| KG_MAX_TOKEN_SIZE | No | Maximum token size for embeddings | 8192 |
| RAG_MCP_TRANSPORT | No | MCP transport protocol (stdio, http, sse, streamable-http) | streamable-http |
| KG_EMBEDDING_MODEL | No | Embedding model | text-embedding-3-large |
| KG_ENABLE_EQUATION | No | Enable equation extraction from PDFs | true |
| KG_MAX_CONCURRENT_FILES | No | Maximum concurrent files for processing | 4 |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
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/serkanyasr/rag-anythink-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server