Schema | Engram

Engram

Describes the environment variables required to run the server.

Name	Required	Description	Default
`ENGRAM_HOST`	No	Listen address (SSE/HTTP)	0.0.0.0
`ENGRAM_PORT`	No	Listen port (SSE/HTTP)	8192
`ENGRAM_DATA_PATH`	No	Root path for knowledge data	/knowledge
`ENGRAM_QUERY_LOG`	No	File path; when set, search/recall append a JSONL trace of each call
`ENGRAM_TRANSPORT`	No	MCP transport (stdio, sse, streamable-http)	stdio
`ENGRAM_PUBLIC_URL`	No	Public base URL for the server (required only if ENGRAM_MULTI_TENANT=1)
`ENGRAM_MULTI_TENANT`	No	Set to 1 to enable multi-tenant mode (requires ENGRAM_PUBLIC_URL and ENGRAM_ADMIN_API_KEY)	0
`ENGRAM_ADMIN_API_KEY`	No	Admin API key to provision teams (required only if ENGRAM_MULTI_TENANT=1)
`ENGRAM_DASHBOARD_HOST`	No	Dashboard listen address	0.0.0.0
`ENGRAM_DASHBOARD_PORT`	No	Dashboard listen port	8193
`ENGRAM_EMBEDDING_MODEL`	No	Model2Vec model for semantic search	minishlab/potion-multilingual-128M
`ENGRAM_ENABLE_DASHBOARD`	No	Set to 1, true, or yes to start the dashboard as a second process alongside the MCP server	0

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/veronchenko/engram-memory'

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