memory-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TZ | No | Time zone used by the brain. | |
| TF_PY | No | Optional command for a rendering page reader for JavaScript-heavy pages. | |
| LLM_URLS | Yes | OpenAI-compatible chat endpoint URL(s) used for model calls. | |
| BRAIN_HOME | No | Directory holding the env file, data, logs and context repo. | ~/.brain |
| CONNECTORS | No | Optional list of connectors to run (e.g. gmail, imessage, calendar, x, omp). With none, the brain starts with captures, skills and notes. | |
| PUBLIC_URL | No | Optional public URL used instead of loopback when connecting clients with --remote. | |
| RERANK_URL | No | Optional URL of the local cross-encoder reranker (llama-server). If unset, reranking is skipped. | |
| LLM_API_KEY | No | API key for the LLM endpoint(s) in LLM_URLS. Alternative to LLM_API_KEY_FILE. | |
| DATABASE_URL | Yes | Postgres connection URL for the brain database (Postgres 17 with pgvector and pg_search). | |
| KEYCHAIN_PREFIX | No | Optional macOS Keychain prefix for storing Postgres role passwords. | |
| LLM_API_KEY_FILE | No | Path to a file containing the LLM API key. Alternative to LLM_API_KEY. |
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
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues