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'). |
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/optimikelabs/optimike-obsidian-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server