広告掲載
MCP.so
ログイン

Strata MCP Server

@agenerationforwordz-tech

リポジトリ

基本情報

カテゴリ

その他

トランスポート

stdio

作者

agenerationforwordz-tech

投稿者

agenerationforwordz-tech

Strata MCP Server について

Strata is a self hosted AI memory server. Your AI remembers everything across every session, on your own hardware.

#ai-memory#mcp-server#self-hosted#local-first#semantic-search#postgresql#raspberry-pi#knowledge-base#ai-agents#vector-search#persistent-memory#mcp#claude#claude-code#codex#ai-assistant#memory-server#embeddings#pgvector#ai-tools#personal-ai#private-ai#local-ai#homelab#self-hosted-ai#ai-knowledge#thought-tracker#note-taking#second-brain#zettelkasten#knowledge-graph#vector-database#similarity-search#cosine-similarity#ai-workflow#agent-memory#llm-memory#llm-tools#context-window#session-memory#ai-continuity#ai-recall#machine-learning#nlp#natural-language#onnx#fastembed#sqlite#api-keys#agent-permissions#kill-switch#audit-log#data-sovereignty#privacy-first#offline-ai#no-cloud#on-premise#raspberry-pi-project#arm64#linux#python#mcp-tools#ai-infrastructure#developer-tools#productivity#automation

接続前の確認

文書確認日：2026-10-25

適した用途

STRATA はセルフホスト型メモリですが、README は SOLUM に置き換えられたと明記しています。新規導入では先に後継を確認してください。

設定と制限

現在の開発状況は上流の SOLUM リンクを参照します。既存データは移行前にバックアップしてください。デモ設定はダッシュボードの空パスワードを許可するため、私用環境に流用しないでください。

リンク先の文書を確認した内容です。認証済みの実接続テストを意味しません。確認手順はご自身の環境で実行してください。

上流ドキュメントを見る関連サーバーを比較

Strata 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": {
    "strata": {
      "type": "http",
      "url": "http://YOUR_HOST:4320/mcp",
      "headers": {
        "X-API-Key": "YOUR_AGENT_KEY"
      }
    }
  }
}

Strata MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンでサーバーのエンドポイントに接続し、ツール一覧を取得できます。

概要

What is Strata?

Strata is a self‑hosted AI memory server that gives any MCP‑compatible AI agent persistent, long‑term memory on your own hardware. It stores thoughts as vector embeddings, provides semantic search, a file vault, and a 3D constellation viewer — and runs on a Raspberry Pi.

How to use Strata?

Clone the repository, create a Python virtual environment, install dependencies (pip install -r requirements.txt), and run python server.py. The web dashboard is accessible at http://localhost:4320/dashboard. Per‑agent API keys can be managed from /admin/agents, and the server can be configured with environment variables such as STRATA_DEMO_MODE=true for a quick demo.

Key features of Strata

  • Semantic search by meaning, not keywords.
  • File vault with attached source files.
  • Per‑agent API keys with granular permissions.
  • PostgreSQL pgvector backend for production scale.
  • 3D Constellation viewer with live activity.
  • Optional AES‑256 encryption at rest.

Use cases of Strata

  • Provide persistent memory for AI coding assistants like Claude Code.
  • Self‑host a personal knowledge base with semantic recall.
  • Audit and trace AI agent actions with daily CSV logs.
  • Attach files to thoughts for project context retrieval.
  • Run entirely on low‑power hardware like a Raspberry Pi 4B.

よくある質問

1

What MCP servers or AI tools does Strata integrate with?

Strata works with any MCP‑compatible AI, including Claude Code, Codex CLI, and other tools that support the Model Context Protocol.

2

Does Strata run on a Raspberry Pi?

Yes, the entire system — semantic search, file storage, and embeddings — runs on a Raspberry Pi 4B with 4 GB of RAM.

3

Where is my data stored?

Data is stored locally in a SQLite or PostgreSQL database (with optional pgvector). You can also enable AES‑256 encryption at rest via SQLCipher.

4

What are the main dependencies?

Strata requires Python, ONNX Runtime, FastEmbed, and optionally PostgreSQL 17 with pgvector for production deployments. Initial install downloads about 700 MB of binary wheels.

5

How do agents authenticate?

Each agent receives a unique API key with granular read/write/delete/admin/kill permissions, managed from the `/admin/agents` panel. A global MCP kill switch can lock all agents out instantly.

コメント

「その他」の他のコンテンツ

Health by Dr Brad

Dr Brad Stanfield

Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one

FastMCP v2 🚀

jlowin

🚀 The fast, Pythonic way to build MCP servers and clients.

26.0K

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

Yuppsy

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K
広告掲載