lily-memory-mcp
by Seizethewind
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SELF_PING | No | Set to 'false' to disable the built-in self-ping that runs every 10 minutes. | true |
| BACKUP_REPO | No | Optional private repository where memories are exported as JSONL via the GitHub API for nightly backups. | |
| GITHUB_TOKEN | Yes | GitHub token used by the GitHub read/write tools. | |
| MCP_BASE_URL | Yes | Base URL of the deployed MCP service. | |
| ALLOWED_REPOS | Yes | Repositories the GitHub token may access. Use '*' for every repo the PAT can reach, or a comma-separated list such as 'Seizethewind/*,UmakraftCircle/*'. | |
| MCP_ADMIN_SECRET | Yes | Admin secret used to approve the custom connector. | |
| TURSO_AUTH_TOKEN | Yes | Turso auth token used for persistent memory. | |
| TURSO_DATABASE_URL | Yes | Turso database URL used for persistent memory. |
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