Recall
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| REDIS_URL | No | Connection URL for the self-hosted Redis backend, e.g. `redis://localhost:6379` or `rediss://default:password@your-redis-host.com:6379`. Use this to store memories in your own Redis instance. | |
| VALKEY_HOST | No | Hostname of the self-hosted Valkey instance (e.g. `localhost`). | |
| VALKEY_PORT | No | Port of the self-hosted Valkey instance (e.g. `6379`). | |
| BACKEND_TYPE | No | The storage backend type to use. Set to `valkey` to use a self-hosted Valkey instance. | |
| RECALL_API_KEY | No | Your Recall Cloud API key (starts with `sk-recall-`). Used when connecting to the managed Recall Cloud service (recallmcp.com) instead of self-hosting. | |
| WORKSPACE_MODE | No | Controls workspace behavior. Set to `hybrid` or `global` to enable globally accessible memories across all workspaces (v1.3+). | |
| ANTHROPIC_API_KEY | No | API key for the embedding provider (Anthropic in the examples). Required depending on the embedding provider you configure; a keyword fallback is available. |
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
ActivityActive
ResponsivenessNo issues