Memorious MCP Server

@cedricvidal

リポジトリ

基本情報

カテゴリ

メモリとナレッジ

トランスポート

stdio

作者

cedricvidal

投稿者

Cedric Vidal

Memorious MCP Server について

Memorious-MCP is a minimal Model Context Protocol (MCP) server that provides a persistent key-value memory store with vector-similarity lookup using ChromaDB.

#memory #semantic#key-value#embedding #chromadb #python

Memorious MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "memorious": {
      "command": "uvx",
      "args": [
        "memorious-mcp"
      ]
    }
  }
}

Memorious MCP Server のツール

Store a user's fact, piece of information, or preference for later recall. IMPORTANT: `key` MUST be short, canonical, and optimized for embedding/vector similarity lookups. Prefer 1–5 words separated by spaces (for example: "likes jazz", "pref cuisine italian", "lives in paris"). Do NOT use long sentences or paragraphs as keys — put long text into `value` instead. This tool SHOULD be called by the LLM whenever the user states a fact, personal detail, or stable preference that the assistant is expected to remember. Guidelines for the LLM: - Call this tool for user-expressed facts, identity details, or explicit preferences that will be useful later. - Use `key` as a short, consistent, space-separated descriptor across related memories to improve retrieval quality (canonicalize synonyms where possible). - Use `value` for the full text of the fact or preference to be stored and returned on recall; include any extra context inside `value`. Privacy: avoid storing highly sensitive data (passwords, social security numbers, bank details) unless the user explicitly requests secure storage and consents.

Retrieve stored memories relevant to a query key. IMPORTANT: To get reliable results the LLM MUST query with the same short, canonical, embedding-optimized keys used at store time. Keys should be compact (1–5 words, space-separated) and represent the core concept — avoid long descriptive queries. If the current user utterance is verbose, the LLM should first map or canonicalize it to an appropriate short key before calling this tool (for example map "I really like listening to jazz music" -> "likes jazz"). This tool SHOULD be called by the LLM when it needs to fetch previously stored facts, personal details, or preferences to inform a response or provide personalized behavior (for example: to recall a user's favorite cuisine before making restaurant suggestions). Parameters: - key: concise, embedding-friendly, space-separated query text used for similarity search. - top_k: maximum number of nearest memories to return. Returns a dict with `results` (memory items including stored value). If nothing matches, `results` is empty.

Delete stored memories that match a query key. IMPORTANT: Deletion operates on short, canonical keys. The LLM MUST issue forget calls using the same concise, embedding-optimized, space-separated key style used to create memories (otherwise relevant memories may not be found). Prefer 1–5 words separated by spaces when requesting deletions. This tool SHOULD be called by the LLM when the user explicitly requests that certain stored information be forgotten or removed (for example: "forget that I live in Paris") or when the assistant decides a memory must be purged because it is incorrect or sensitive. Parameters: - key: concise, canonical, space-separated query text used to find candidate memories to delete. - top_k: number of nearest matches to consider for deletion. Behavior: - Deletion is irreversible; the LLM should confirm with the user when intent is ambiguous before invoking this tool. - The tool returns `deleted_ids` for the memories that were removed.

概要

What is Memorious MCP?

Memorious MCP is a local and persistent semantic memory server for AI assistants using the Model Context Protocol (MCP). It uses ChromaDB for vector similarity search and FastMCP for efficient tool implementation, and runs entirely on your machine—no data ever leaves it.

How to use Memorious MCP?

Install via uvx memorious-mcp or set up in a virtual environment with uv sync and uv run memorious-mcp. Add the server to your MCP client configuration with the command uvx and arguments ["memorious-mcp"]. Use the three built-in tools: store, recall, and forget.

Key features of Memorious MCP

100% local and private – all processing stays on your machine
Persistent memory across sessions using ChromaDB disk-based storage
Semantic search via vector embeddings for similarity-based retrieval
Simple three-tool API for memory management
FastMCP integration for efficient MCP server implementation
Canonical key design optimized for short, embedding-friendly keys
No external API calls or cloud dependencies required

Use cases of Memorious MCP

Personal assistant memory – remember user preferences, habits, and personal information
Context preservation – maintain conversation context across sessions
Knowledge management – store and retrieve project-specific information
Personalization – enable AI assistants to provide tailored responses based on stored preferences
Privacy‑first AI – keep sensitive personal data local while still having persistent memory

よくある質問

How does Memorious MCP ensure privacy?

All data processing and storage happens locally on your machine—no network requests, no cloud dependencies, and no data ever leaves your computer.

What are the system requirements?

Python version 3.12 or higher is required. The server uses ChromaDB and FastMCP, which are installed automatically.

Where is my data stored?

Data is stored in the `./.memorious` directory (configurable) using ChromaDB’s persistent disk-based storage.

「メモリとナレッジ」の他のコンテンツ

ctxfile

Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.

Azquo

Azquo Holdings Ltd

Exact, shared memory for AI agents: a hierarchical database where totals always add up, every write is attributed to the agent and person behind it, and any figure traces back to its source file. Agents create databases,

agentleFS

One permissioned folder your team and your AI agents both log into.

Sooveryn

PANDAPROG

Sooveryn gives Claude Code a team of AI personas that remembers your project. Soov, the partner and team lead, keeps your decisions and how you work in a lasting memory, and finds them again by words and by meaning, from

Leviathan Systems Public Content MCP

Leviathan Systems

Search published GPU deployment, rack integration and structured cabling resources; read canonical documents and Leviathan Systems company service scope. Anonymous, read-only Streamable HTTP MCP. No credentials required.