Recall
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| REDIS_URL | No | Connection URL of the Redis backend used for self-hosted memory storage, e.g. redis://localhost:6379 or rediss://default:password@your-redis-host.com:6379 for TLS. | |
| VALKEY_HOST | No | Hostname of the Valkey instance, e.g. localhost. | |
| VALKEY_PORT | No | Port of the Valkey instance, e.g. 6379. | |
| BACKEND_TYPE | No | Set to `valkey` to use a Valkey backend instead of the default Redis backend, e.g. "BACKEND_TYPE": "valkey". | |
| RECALL_API_KEY | No | Your Recall Cloud API key from the dashboard at recallmcp.com/dashboard (starts with `sk-recall-`). Used as `Authorization: Bearer <key>` when connecting to https://recallmcp.com/mcp. | |
| WORKSPACE_MODE | No | Workspace behaviour for memory storage. Set to `hybrid` to allow both workspace and global memories, or `global`. Required only if you want to store memories globally (v1.3+). | workspace |
| ANTHROPIC_API_KEY | No | Your Anthropic API key, used for embeddings. Optional — an Anthropic keyword fallback is used when no embedding provider is configured. |
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
ResponsivenessResponsive