Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LOG_LEVELNolog levels (debug, info, warn, error)info
CLIP_MODELNoEmbedding model nameXenova/clip-vit-base-patch32
STRIP_EXIFNoStrip EXIF metadata from stored screenshotstrue
STRICT_MODENoRefuse external L4 calls & enforce projectRoot pathsfalse
LANCEDB_PATHNoStorage path for LanceDB.vision-memory-mcp
OFFLINE_MODENoRestrict CLIP loading to local files onlyfalse
OPENAI_API_KEYNoRequired if using OpenAI endpoints for L4 fallback
TTL_DEFAULT_MSNoEviction TTL (default: 7 days)604800000
CLIP_MODEL_PATHNoOptional local path to pre-downloaded CLIP model
VISION_MODEL_NAMENoVision model identifiergpt-4o
LANCEDB_CACHE_SIZENoMaximum hot items in LRU Cache100
LIMIT_INPUT_PIXELSNoSharp decompression bomb pixel limit16777216
MAX_LANCEDB_SIZE_MBNoEviction threshold (MB)1000
EMBEDDING_DIMENSIONSNoCLIP embedding output dimension512
HASH_EXACT_THRESHOLDNoHamming distance <= this = exact hit5
VISION_MODEL_ENABLEDNoEnable L4 vision fallbackfalse
VISION_MODEL_ENDPOINTNoVision model server URLhttp://localhost:1234/v1
HASH_SIMILAR_THRESHOLDNoHamming distance <= this = similar hit10

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/putervision/vision-memory-mcp'

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