engram-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@engram-mcpsearch my conversations about react hooks"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
engram-mcp
Claude Codeの会話履歴をローカルでセマンティック検索できるMCPサーバー。
Features
Hybrid Search: FTS5(キーワード検索)+ sqlite-vec(ベクトル検索)のRRF融合
Local Embeddings: Ollama (nomic-embed-text) によるローカル埋め込み生成
Time Decay: 古い記憶は検索スコアが減衰
Auto Save: セッション終了時に会話を自動保存(hooks連携)
Related MCP server: ClaudeHistoryMCP
Requirements
Node.js 20+
Ollama with
nomic-embed-textmodel
ollama pull nomic-embed-textInstallation
git clone https://github.com/lowbridgee/engram-mcp.git ~/.claude/memory
cd ~/.claude/memory
npm install
npm run build
npm run init-dbConfiguration
1. MCP Server設定
claude mcp add コマンドで登録する(全プロジェクト共通にするには --scope user):
claude mcp add --scope user engram-memory node /Users/$(whoami)/.claude/memory/dist/mcp_server.js登録確認:
claude mcp list2. Auto-save Hook設定
~/.claude/settings.json の hooks セクションに追加する。~ はNode.jsで展開されないため絶対パスを使うこと:
{
"hooks": {
"Stop": [
{
"hooks": [
{
"type": "command",
"command": "node /Users/YOUR_USERNAME/.claude/memory/dist/save_session.js"
}
]
}
]
}
}Usage
MCP Tools
Claude Code内で以下のツールが使用可能:
search_memory: 過去の会話をハイブリッド検索(結果にはIDが付与され、500文字以上は[truncated]表示)get_memory: 指定したIDのメモリ全文を取得(truncatedされた内容を見たいときに使用)memory_stats: データベースの統計情報を表示
Manual Save
特定のセッションを手動で保存:
npm run save -- <session_id>Architecture
┌─────────────────┐ ┌─────────────────┐
│ Claude Code │────▶│ engram-mcp │
│ (MCP Client) │ │ (MCP Server) │
└─────────────────┘ └────────┬────────┘
│
┌────────────────────────┼────────────────────────┐
▼ ▼ ▼
┌───────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ memories │ │ memories_fts │ │ memories_vec │
│ (main table) │ │ (FTS5) │ │ (sqlite-vec) │
└───────────────┘ └─────────────────┘ └─────────────────┘
│
▼
┌─────────────────┐
│ Ollama │
│ nomic-embed-text│
└─────────────────┘Database Schema
-- Main table
CREATE TABLE memories (
id INTEGER PRIMARY KEY,
session_id TEXT NOT NULL,
project_path TEXT,
turn_index INTEGER NOT NULL,
user_message TEXT,
assistant_message TEXT,
created_at DATETIME DEFAULT CURRENT_TIMESTAMP
);
-- FTS5 for keyword search (trigram tokenizer)
CREATE VIRTUAL TABLE memories_fts USING fts5(...);
-- sqlite-vec for semantic search (768-dim embeddings)
CREATE VIRTUAL TABLE memories_vec USING vec0(
memory_id INTEGER,
embedding FLOAT[768]
);License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Search your AI chat history (ChatGPT, Claude, Codex) from any MCP client. Remote, private, read-only
Private persistent memory for Claude, ChatGPT & Gemini via MCP - semantic search, zero-code setup.
An MCP server that gives your AI access to the source code and docs of all public github repos
Related MCP Servers
- AlicenseAqualityCmaintenanceAn MCP server that provides dynamic codebase context to Claude Code through tools like hybrid search, recent changes, and symbol definitions, enhancing AI-assisted coding with local RAG.8MIT
- AlicenseAqualityDmaintenanceAn MCP server that makes Claude Code conversation history searchable and proactively useful by indexing past sessions with hybrid BM25+TF-IDF search, extracting decisions and solutions, and auto-injecting relevant project context at session start.9666MIT
- FlicenseAqualityDmaintenanceA semantic search system for Claude Code transcript history, exposed as an MCP server so Claude Code can query its own past sessions.2-
- AlicenseNot gradedqualityDmaintenanceA local MCP server that indexes and searches your Claude Code conversation history with both keyword and semantic search, fully private and running locally.MIT