obsidian-rag-mcp
by AdrianBodrug
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RAG_DB_PATH | No | Derived index; safe to delete | ./rag_data |
| RAG_AUTO_SYNC | No | Sync changed notes before each search | true |
| OPENAI_API_KEY | No | Required only for openai provider | |
| RAG_CHUNK_SIZE | No | Maximum characters per chunk | 3500 |
| RAG_CHUNK_OVERLAP | No | Characters shared with the next chunk (0 allowed) | 350 |
| RAG_MIN_SIMILARITY | No | Drop vector matches below this cosine similarity | 0 |
| OBSIDIAN_VAULT_PATH | Yes | Vault root (required) | |
| RAG_EMBEDDING_MODEL | No | Embedding model, defaults per provider (e.g., Xenova/bge-small-en-v1.5 for local, text-embedding-3-small for openai) | |
| RAG_EXCLUDE_FOLDERS | No | Comma-separated, vault-relative; nested paths allowed | Templates |
| RAG_EMBEDDING_PROVIDER | No | local, openai, or local-hash (offline, keyword hashing) | local |
| RAG_MAX_CHUNKS_PER_NOTE | No | Cap per note in search results | 2 |
| RAG_EMBEDDING_DIMENSIONS | No | Embedding dimensions, defaults per provider (384 for local, 1536 for openai, 256 for local-hash) |
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 | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues