Mnemo - Persistent AI Memory
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DB_PATH | No | Database location | ~/.mnemo-mcp/memories.db |
| API_KEYS | No | API keys (ENV:key,ENV:key). Optional: enables semantic search (SDK mode) | |
| LOG_LEVEL | No | Log level | INFO |
| SYNC_FOLDER | No | Remote folder | mnemo-mcp |
| SYNC_REMOTE | No | rclone remote name | gdrive |
| SYNC_ENABLED | No | Enable rclone sync | false |
| SYNC_INTERVAL | No | Auto-sync seconds (0=manual) | 300 |
| SYNC_PROVIDER | No | rclone provider type (drive, dropbox, s3, etc.) | drive |
| EMBEDDING_DIMS | No | Embedding dimensions (0 = auto-detect, default 768) | 0 |
| EMBEDDING_MODEL | No | LiteLLM model name (optional) | |
| EMBEDDING_API_KEY | No | Custom embedding endpoint key (optional) | |
| EMBEDDING_BACKEND | No | litellm (cloud API) or local (Qwen3). Auto: API_KEYS -> litellm, else local (always available) | (auto-detect) |
| LITELLM_PROXY_KEY | No | LiteLLM Proxy virtual key (e.g. sk-...) | |
| LITELLM_PROXY_URL | No | LiteLLM Proxy URL (e.g. http://10.0.0.20:4000). Enables proxy mode | |
| EMBEDDING_API_BASE | No | Custom embedding endpoint URL (optional, for SDK mode) |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| add_memoryA | Store NEW information. Use for preferences, decisions, facts. ACTION GUIDE — when to use:
|
| search_memoryA | Find existing memories by natural language query. Always search before adding. ACTION GUIDE — when to use:
|
| list_memoriesA | Browse all memories, optionally filtered by category. ACTION GUIDE — when to use:
|
| update_memoryA | Modify an EXISTING memory by ID. Get memory_id from search results. ACTION GUIDE — when to use:
|
| delete_memoryA | Remove a memory by ID. ACTION GUIDE — when to use:
|
| export_memoriesA | Export all memories as JSONL. ACTION GUIDE — when to use:
|
| import_memoriesA | Import memories from JSONL data or a list of objects. ACTION GUIDE — when to use:
|
| memory_statsA | Show database statistics (total memories, categories, embedding status). ACTION GUIDE — when to use:
|
| restore_memoryA | Restore an archived memory by ID. ACTION GUIDE — when to use:
|
| archived_memoriesB | List archived memories. ACTION GUIDE — when to use:
|
| consolidate_memoriesA | Summarize similar memories in a category (requires LLM API keys). ACTION GUIDE — when to use:
|
| memoryA | [DEPRECATED — use the granular tools (add_memory, search_memory, ...) instead; this composite tool will be removed in a future release] Legacy dispatcher for backward compatibility. Use specialized tools (add_memory, search_memory, etc.) instead. Persistent memory store. Actions: add|search|list|update|delete|export|import|stats|restore|archived|consolidate. ACTION GUIDE — when to use each:
WORKFLOW: search -> not found? -> add. Found outdated? -> update (with memory_id from results). PROACTIVE: save user preferences, decisions, corrections, project conventions. |
| configA | Server config, sync, and setup. Actions: status|sync|set|warmup|setup_sync. ACTION GUIDE — when to use each:
|
| helpA | Full documentation for memory and config tools. topic: 'memory' | 'config' ACTION GUIDE — when to use:
|
| config__open_relayB | Open the relay configuration form for mnemo-mcp in the user's browser. Returns the relay URL, whether the browser launched, and the current status. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| save_summary | Generate a prompt to save a conversation summary as memory. ACTION GUIDE — when to use: - Use when a conversation is concluding or shifting topics to persist key takeaways. - Parameters: 'summary' (the consolidated text to save). |
| recall_context | Generate a prompt to recall relevant memories about a topic. ACTION GUIDE — when to use: - Use when starting a new task or answering a question to retrieve prior context. - Parameters: 'topic' (the specific subject or keywords to search for). |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/n24q02m/mnemo-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server