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 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
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
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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