LLM Second Brain
by philadelfic
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | HTTP port for the server. | 8080 |
| DB_PATH | No | Path to the SQLite database file. | /data/notes.db |
| MCP_PATH | No | Path for the MCP Streamable HTTP endpoint. | /mcp |
| LOG_LEVEL | No | Log level for JSON stdout logs. | INFO |
| BACKUP_DIR | No | Directory where periodic database backups are stored. | /data/backups |
| CHUNK_SIZE | No | Chunk size in tokens. | 1024 |
| BACKUP_KEEP | No | Number of recent backups to retain. | 7 |
| CHUNK_OVERLAP | No | Token overlap between chunks. | 180 |
| EMBEDDING_DIM | No | Dimension of the embedding vectors. | 4096 |
| SNIPPET_CHARS | No | Number of characters included in search snippets (mentioned in README; no default specified). | |
| SUMMARY_MODEL | Yes | Model name used for summarization, e.g. ornith-1.5:35b. Required. | |
| TEXT_SPLITTER | No | Token splitter used for chunking. | tiktoken |
| MAX_NOTE_CHARS | No | Maximum number of characters allowed for a note. | 35000 |
| MCP_AUTH_TOKEN | Yes | Bearer token for all MCP endpoints except /health. Required. Empty token is a fatal startup error. | |
| EMBEDDING_MODEL | No | Embedding model used for vectorization. | qwen3-embedding:8b |
| MAX_QUERY_CHARS | No | Maximum number of characters allowed for a search query. | 512 |
| OLLAMA_BASE_URL | Yes | Base URL of the Ollama instance used for embeddings (e.g. http://host:11434). Required. | |
| CHUNK_MIN_TARGET | No | Minimum token count for the tail chunk before merging. | 200 |
| BACKUP_INTERVAL_SEC | No | Interval in seconds between database backups. | 86400 |
| EMBEDDING_BATCH_SIZE | No | Number of chunks sent in a single embed request. | 32 |
| SUMMARY_OLLAMA_BASE_URL | Yes | Base URL of the Ollama instance used for summarization. Required. | |
| EMBEDDING_CONCURRENT_REQUESTS | No | Maximum number of concurrent embedding requests. | 3 |
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/philadelfic/LLM-second-brain'
If you have feedback or need assistance with the MCP directory API, please join our Discord server