memos-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MEMOS_URL | No | MemOS HTTP base URL | http://localhost:8000 |
| MEMOS_AUTHOR | No | Author tag stamped on every entry | human |
| MEMOS_ORIGIN | No | Origin tag (e.g. vscode, cursor, claude-code) | vscode |
| MEMOS_CUBE_ID | No | Paperclip companyId — used as MemOS cube | Animus Group UUID |
| MEMOS_USER_ID | No | MemOS user_id scope (default: shared with agent KB) | kb-${MEMOS_CUBE_ID} |
| MEMOS_TIMEOUT_SEC | No | HTTP request timeout | 15 |
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 |
|---|---|
| memos_rememberA | Store a memory in MemOS, visible to both human and Paperclip agent searches. The content is sanitized (credentials, API keys, tokens, JWTs etc. are redacted) before being stored. Use this to capture decisions, conventions, debugging insights, or anything you want to recall later — or want your Paperclip agents to know about on their next run. Args: content: The text to remember. Will be auto-sanitized for credentials. category: One of decision, learning, fact, preference, note, convention. project: Optional project tag, e.g. "paperclip", "accounts", "memos". tags: Optional free-form tag list. |
| memos_searchA | Search MemOS for memories matching a query. Returns the top matches as a markdown list with score, source, category, project, and content excerpt. Searches the same scope that Paperclip agents read from, so results include both human notes and any agent KB entries (completed issues, executive briefs, indexed documents). Args: query: Natural language query, e.g. "rename routine convention". top_k: Maximum number of results to return (default 5, max 25). only_human: If True, filter results to entries with [source: human]. Use this when you specifically want notes Seth wrote, not agent runs. |
| memos_recentA | List recent memories from the last N hours. Useful for "what was I working on yesterday?". Searches with a wildcard query then sorts client-side by stored_at timestamp. Args: hours: How many hours back to look (default 24). source: Optional filter on the [source: ...] tag, e.g. "human". |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool serves a clear, distinct purpose: storing memories, retrieving recent ones, and searching by query. No overlap exists between the three operations.
All tools follow a consistent 'memos_<verb>' pattern (remember, recent, search), making the naming predictable and easy to understand.
With 3 tools, the count is slightly on the low side but appropriate for a focused memory server. It covers the core operations without unnecessary bloat.
The tool set lacks update and delete operations, which are notable gaps for a complete memory management system. However, the retrieval and creation tools are well-implemented.