Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
VAULT_ROOTYesThe single allowlisted Markdown root
VAULT_AUDIT_PATHNoJSONL audit location (default: OS state directory)
VAULT_INDEX_PATHNoSQLite index location (default: OS cache directory)
VAULT_MAX_RESULTSNoHard cap on search results10
VAULT_EXCLUDE_DIRSNoDirectory names skipped recursively.git,.obsidian,.trash,.venv,__pycache__,node_modules
VAULT_MAX_FILE_BYTESNoPer-note indexing and read limit1000000
VAULT_MAX_READ_CHARSNoMaximum text returned by one read20000
VAULT_EMBEDDING_MODELNoLocal Sentence Transformers modelintfloat/multilingual-e5-small
VAULT_AUDIT_QUERY_TEXTNoStore raw searches instead of hashesfalse
VAULT_EMBEDDING_DEVICENoTorch device used for embeddingscpu
VAULT_MODEL_LOCAL_FILES_ONLYNoRefuse model-network access; enable after the model is cachedfalse

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/rickquant/vault-rag-mcp'

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