Optimike Obsidian MCP
by optimikelabs
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_AUTH_MODE | No | Authentication mode: none, jwt, oauth (default none for local). | |
| MCP_HTTP_HOST | No | HTTP server host (default 127.0.0.1). | |
| MCP_HTTP_PORT | No | HTTP server port (default 3010). | |
| SMART_ENV_DIR | No | Path to the .smart-env directory for semantic search. | |
| MCP_WRITE_MODE | No | Write safety: readonly, guarded, full (default full). | |
| OBSIDIAN_VAULT | No | Path to the Obsidian vault. Falls back to parent of .smart-env directory or project root. | |
| OPENAI_API_KEY | No | API key for OpenAI embeddings. | |
| QUERY_EMBEDDER | No | Embedding provider: auto, ollama, openai, xenova (default auto). | |
| OLLAMA_BASE_URL | No | Base URL for Ollama (default http://127.0.0.1:11434). | |
| OBSIDIAN_API_KEY | No | API key for Obsidian Local REST API plugin (required for live mode). | |
| OBSIDIAN_BASE_URL | No | Base URL for Obsidian Local REST API (default http://127.0.0.1:27123). | |
| MCP_ALLOWED_ORIGINS | No | Allowed CORS origins (default narrow for localhost). | |
| QUERY_EMBEDDER_MODEL | No | Model name for embedding (e.g., text-embedding-3-small). | |
| OBSIDIAN_CACHE_SOURCE | No | Cache refresh source: auto, filesystem, rest (default auto). | |
| OBSIDIAN_RUNTIME_MODE | No | Runtime mode: live, hybrid, headless-readonly, headless-guarded, headless-filesystem (default live). | |
| ENABLE_QUERY_EMBEDDING | No | Enable query embedding for semantic search (default 'true'). | |
| SEMANTIC_SEARCH_PREWARM | No | Disable startup prewarm of semantic search (default 'true'). | |
| OBSIDIAN_STARTUP_BLOCKING | No | Block startup until health check passes (default 'true'). | |
| MCP_PROXY_START_TIMEOUT_MS | No | Timeout for proxy startup in ms (default 20000). | |
| OBSIDIAN_CACHE_CONCURRENCY | No | Concurrency for filesystem cache refresh. | |
| MCP_GUARDED_MAX_WRITE_CHARS | No | Max characters allowed in guarded mode writes. | |
| OPENAI_EMBEDDING_DIMENSIONS | No | Dimensions for OpenAI embeddings (e.g., 1024). | |
| OBSIDIAN_STARTUP_MAX_RETRIES | No | Max retries for startup health check. | |
| OBSIDIAN_SHARED_CACHE_DB_PATH | No | Path to shared SQLite cache (default <vault>/.obsidian/optimike-mcp/shared-cache.sqlite). | |
| OBSIDIAN_STARTUP_RETRY_DELAY_MS | No | Delay between startup retries in ms. | |
| OBSIDIAN_VAULT_EXCLUDE_PATTERNS | No | Comma- or newline-separated gitignore-style exclusion patterns. | |
| MCP_GUARDED_MAX_BATCH_OPERATIONS | No | Max batch operations allowed in guarded mode. | |
| OBSIDIAN_CONTENT_HOT_CACHE_LIMIT | No | Bounded in-memory hot set limit (default 64? example shows '64'). |
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/optimikelabs/optimike-obsidian-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server