Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CONTEXT_CHUNK_SIZENoToken size for memory chunks.3200
CONTEXT_MAX_TOKENSNoMaximum number of tokens for context packing.12000
DATABASE_NEO4J_URLNoNeo4j server URL (optional).
CONTEXT_TOKEN_MODELNoTokenization model name.cl100k_base
DATABASE_NEO4J_USERNoNeo4j username (optional).
DATABASE_QDRANT_URLNoQdrant server URL (optional, not used in MVP).
DATABASE_SQLITE_PATHNoPath to the SQLite database file../data/memory.db
DATABASE_NEO4J_PASSWORDNoNeo4j password (optional).
CONTEXT_RELIEF_PERCENTAGENoPercentage of tokens to evict during relief.0.4
CONTEXT_PRESSURE_THRESHOLDNoThreshold for pressure relief (fraction of max tokens).0.8
DATABASE_QDRANT_COLLECTIONNoQdrant collection name (optional).

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/elevend0g/cont3xt'

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