Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
AXON_PROJECTNoProject slug that scopes the MCP server (lowercase, may contain /, e.g. acme/api). When set, the project argument becomes optional on every tool.
DATABASE_URLYesPostgres connection URL used by the server, e.g. postgres://axon:axon@localhost:54329/axon. Required for a stdio MCP server; may be supplied via .env.
AXON_MAX_LINKSNoMaximum number of links per memory. Defaults to 32.32
AXON_EMBED_MODELNoEmbedding model name. Defaults to Qwen3-Embedding-0.6B. After changing it, run axon reembed.Qwen3-Embedding-0.6B
AXON_MAX_MEMORIESNoMaximum number of active memories per project. If unset, memory is unlimited; when set, remember fails at the cap with 422 and warns from 90% of the cap.
AXON_ENCRYPTION_KEYNo32-byte base64 key (openssl rand -base64 32) used to encrypt memory title, body and source with AES-256-GCM. If set, new writes are encrypted; losing the key means losing the text.
AXON_DEDUP_SIMILARITYNoSimilarity threshold for duplicate/overlap detection. remember flags likely overlaps at this score minus 0.1, and review lists likely duplicates at the same floor.
AXON_SEARCH_MIN_SIMILARITYNoMinimum cosine similarity for vector-only search hits; lower-scoring vector hits are dropped.

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