Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoHTTP port for the server.8080
DB_PATHNoPath to the SQLite database file./data/notes.db
MCP_PATHNoPath for the MCP Streamable HTTP endpoint./mcp
LOG_LEVELNoLog level for JSON stdout logs.INFO
BACKUP_DIRNoDirectory where periodic database backups are stored./data/backups
CHUNK_SIZENoChunk size in tokens.1024
BACKUP_KEEPNoNumber of recent backups to retain.7
CHUNK_OVERLAPNoToken overlap between chunks.180
EMBEDDING_DIMNoDimension of the embedding vectors.4096
SNIPPET_CHARSNoNumber of characters included in search snippets (mentioned in README; no default specified).
SUMMARY_MODELYesModel name used for summarization, e.g. ornith-1.5:35b. Required.
TEXT_SPLITTERNoToken splitter used for chunking.tiktoken
MAX_NOTE_CHARSNoMaximum number of characters allowed for a note.35000
MCP_AUTH_TOKENYesBearer token for all MCP endpoints except /health. Required. Empty token is a fatal startup error.
EMBEDDING_MODELNoEmbedding model used for vectorization.qwen3-embedding:8b
MAX_QUERY_CHARSNoMaximum number of characters allowed for a search query.512
OLLAMA_BASE_URLYesBase URL of the Ollama instance used for embeddings (e.g. http://host:11434). Required.
CHUNK_MIN_TARGETNoMinimum token count for the tail chunk before merging.200
BACKUP_INTERVAL_SECNoInterval in seconds between database backups.86400
EMBEDDING_BATCH_SIZENoNumber of chunks sent in a single embed request.32
SUMMARY_OLLAMA_BASE_URLYesBase URL of the Ollama instance used for summarization. Required.
EMBEDDING_CONCURRENT_REQUESTSNoMaximum 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

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

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/philadelfic/LLM-second-brain'

If you have feedback or need assistance with the MCP directory API, please join our Discord server