Recall
by Vieira37
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| REDIS_URL | No | Redis connection URL used for self-hosted storage, e.g. `redis://localhost:6379` (use `rediss://` for TLS). | |
| VALKEY_HOST | No | Hostname of the Valkey server to connect to when `BACKEND_TYPE=valkey`, e.g. `localhost`. | |
| VALKEY_PORT | No | Port of the Valkey server to connect to when `BACKEND_TYPE=valkey`, e.g. `6379`. | |
| BACKEND_TYPE | No | Storage backend to use. Set to `valkey` to use Valkey instead of Redis (default is Redis). | redis |
| RECALL_API_KEY | No | Your Recall Cloud API key (starts with `sk-recall-`), used to connect to the managed service at https://recallmcp.com/mcp instead of self-hosting. | |
| WORKSPACE_MODE | No | Controls workspace scoping of memories. Set to `hybrid` or `global` to enable storing and retrieving global memories across all workspaces (v1.3+). | |
| ANTHROPIC_API_KEY | No | Anthropic API key used for embeddings / the Anthropic keyword fallback. |
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