広告掲載
MCP.so
ログイン
R

Ratary Memory MCP Server

@ontorata

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

ontorata

投稿者

ontorata

Ratary Memory MCP Server について

Ratary is an open-source AI Brain Platform. The Memory MCP server (ratary) gives coding assistants durable, owner-scoped memory across sessions — hybrid search, knowledge graph traversal, and token-efficient context assembly.

#memory#development#ai-coding-assistant

Ratary Memory 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": {
    "ratary": {
      "command": "npx",
      "args": [
        "-y",
        "@ratary/mcp-server"
      ],
      "env": {
        "RATARY_BASE_URL": "https://ratary.ontorata.com",
        "RATARY_API_KEY": "aic_..."
      }
    }
  }
}

Ratary Memory MCP Server のツール

6

Return the Ratary deployment capability manifest (protocol version, tool count, limits, feature flags). Read-only and idempotent; requires RATARY_API_KEY. Use at session start to discover what this deployment supports. Do not use for recalling memories — use search_memory or get_context instead. Returns a JSON capability object (no side effects).

Search persistent coding memories with hybrid ranking and return ranked hits (id, title, summary, relevance). Read-only; does not create or modify memories. Requires RATARY_API_KEY. Use when you need candidate memories matching a keyword/question before answering. Prefer get_memory when you already have a memory UUID. Prefer get_context when you need token-bounded context assembled for a task (not a raw hit list). Returns JSON search results; empty list means no matches.

Create a new persistent coding memory (title + markdown body) scoped to an optional project and tags. Side effect: writes a new record via the Ratary REST API; not idempotent (each call creates another memory). Requires RATARY_API_KEY. Does not overwrite existing memories — use get_memory/search_memory first if updating. Use after decisions, handoffs, or durable facts the agent should recall later. Do not use for ephemeral chat notes that should not persist. Returns the created memory JSON including id/codename/timestamps.

Fetch one memory by UUID, including full content and metadata. Read-only and idempotent; requires RATARY_API_KEY. Use when you already know the memory id (from search_memory or a prior save_memory). Do not use for keyword discovery — use search_memory. Do not use to assemble multi-memory task context — use get_context. Returns the memory JSON or an API error if the id is missing.

Assemble token-efficient ranked context for a coding task from persistent memories (summaries by default). Read-only; does not write memories. Requires RATARY_API_KEY. Use at the start of implementation or when answering with organizational memory. Prefer search_memory when you need raw ranked hits to inspect individually. Prefer get_memory for a known UUID. Returns markdown/JSON context suitable for injecting into the agent prompt.

List certified external agent client profiles registered with this Ratary deployment (name, transport, status). Read-only and idempotent; requires RATARY_API_KEY. Use for ecosystem/discovery questions about which clients are supported. Do not use for memory CRUD or retrieval — use save_memory / search_memory / get_context. Returns a JSON list of client profiles (no side effects).

概要

What is Ratary Memory Mcp?

Ratary Memory Mcp is an open-source AI Brain Platform that provides coding assistants with durable, owner-scoped memory across sessions. It combines hybrid search, knowledge graph traversal, and token-efficient context assembly.

How to use Ratary Memory Mcp?

Install via npm (@ratary/mcp-server) for a REST proxy with 6 tools, or clone the repository for local stdio with 28 tools. Self-host using D1, Postgres, Supabase, MariaDB, or Docker. An optional remote Streamable HTTP transport is available when deployed.

Key features of Ratary Memory Mcp

  • Durable, owner-scoped memory across sessions
  • Hybrid search and knowledge graph traversal
  • Token-efficient context assembly
  • Self-hostable with multiple database backends
  • Multiple transport options: stdio, REST proxy, Streamable HTTP

Use cases of Ratary Memory Mcp

  • Persistent memory for coding assistants between sessions
  • Hybrid search over past project context
  • Knowledge graph traversal to find relational data
  • Token-efficient context assembly for LLM conversations

よくある質問

1

What is Ratary Memory Mcp?

It is an open-source platform that gives coding assistants durable, owner-scoped memory across sessions using hybrid search, knowledge graph traversal, and token-efficient context assembly.

2

What transports does Ratary Memory Mcp support?

Local stdio with 28 tools (clone repo), npm package `@ratary/mcp-server` as a REST proxy with 6 tools, and optional remote Streamable HTTP when deployed.

3

How can I self-host Ratary Memory Mcp?

You can self-host using D1, Postgres, Supabase, MariaDB, or Docker.

4

Is Ratary Memory Mcp open source?

Yes, Ratary is an open-source AI Brain Platform.

5

What are the runtime or database requirements?

It supports D1, Postgres, Supabase, MariaDB, or Docker for self-hosting. The npm version acts as a REST proxy.

コメント

「メモリとナレッジ」の他のコンテンツ

Neither MCP

stonianua

Project context your AI can query through MCP — with source evidence.

Semantic Ui React

Semantic-Org

The official Semantic-UI-React integration

13.2K

PLUR

plur-ai

AI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference

226

Code Graph Rag

vitali87

The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs

5.3K

Codebase Memory

DeusData

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 162 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

46.7K
広告掲載