Recall
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| REDIS_URL | No | Connection URL for your Redis instance used as the memory backend, e.g. redis://localhost:6379 or rediss://default:password@your-redis-host.com:6379 (use rediss:// for TLS). | |
| VALKEY_HOST | No | Hostname of your Valkey instance (e.g. localhost). | |
| VALKEY_PORT | No | Port of your Valkey instance (e.g. 6379). | |
| BACKEND_TYPE | No | Backend type to use. Set to "valkey" to use a Valkey instance instead of Redis. | |
| RECALL_API_KEY | No | Your Recall Cloud API key (starts with sk-recall-). Required when using the managed cloud service at https://recallmcp.com/mcp. Set this environment variable to authenticate (equivalent to the `Authorization: Bearer <key>` header). | |
| WORKSPACE_MODE | No | Optional workspace scoping mode. Set to "hybrid" or "global" to enable global memories (memory may be stored/retrieved across all workspaces). | |
| ANTHROPIC_API_KEY | No | Your Anthropic API key, used for embeddings/generation in self-hosted deployments. |
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
ResponsivenessResponsive