広告掲載
MCP.so
ログイン

Frinus MCP Server

@frinus-ai

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

frinus-ai

投稿者

Renato Diniz

Frinus MCP Server について

MCP server that exposes 70 tools spanning cognitive memory, working memory, sessions, agents, the L0–L3 knowledge hierarchy, orchestration tasks, and training pipelines. The server speaks stdio and is consumed by Claude Desktop, Claude Code, OpenCodex, and any MCP-aware client.

Frinus 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": {
    "frinus": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "frinus-mcp@latest"
      ],
      "env": {
        "FRINUS_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}

Frinus 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。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is Frinus?

Frinus is an MCP server that bridges your MCP client (Claude Code, Cursor, Claude Desktop) with the Frinus platform (frinus.rdxsec.com.br), giving your agent long-term cognitive memory. It stores nothing locally and exposes 70 tools for memory, sessions, agents, knowledge hierarchy, orchestration, and training.

How to use Frinus?

You need a free Frinus account and an API key (sk-frinus-...). Add the server to your client via npx, setting the FRINUS_API_KEY environment variable. No installation is needed—npx fetches and runs the package on demand.

Key features of Frinus

  • 70 MCP tools spanning memory, sessions, agents, and training.
  • Cognitive long-term memory: episodic, semantic, procedural.
  • Working memory with automatic eviction and TTL.
  • Semantic search with attention weighting by task type.
  • Stream capture pipeline that promotes items to permanent memory.
  • Seven protocols (BOOT, CONSULT, PLAN, CAPTURE, LEARN, AUDIT, CLOSE).
  • Built-in consolidation, conflict detection, and hierarchy management.

Use cases of Frinus

  • Give Claude agent persistent memory across sessions without losing context.
  • Store and retrieve project knowledge, decisions, and procedures.
  • Capture ongoing work streams and automatically promote important learnings.
  • Maintain structured hierarchies of memories (L0–L3).
  • Orchestrate multi-step tasks with working state and session management.

よくある質問

1

What is Frinus MCP?

It is a bridge between your MCP client and the Frinus hosted platform (https://frinus.rdxsec.com.br), providing long-term cognitive memory for AI agents.

2

How do I get an API key?

Log in to your Frinus account, go to Settings → API Keys, and create a new key. It will look like `sk-frinus-...` and is shown only once.

3

Do I need a Frinus account?

Yes. Sign up at https://frinus.rdxsec.com.br. The Free plan (R$0) includes 100 memories and 20 queries per day, no credit card required.

4

Where are my memories stored?

All memories live on the Frinus platform (hosted SaaS). The server stores nothing locally—every tool call is forwarded over HTTPS.

5

What are the system requirements?

You need an MCP-aware client (e.g., Claude Code, Cursor, Claude Desktop) and a Frinus account with an API key. The server runs via `npx`, so Node.js must be installed.

コメント

「メモリとナレッジ」の他のコンテンツ

Memory

modelcontextprotocol

Model Context Protocol Servers

88.1K

Agimem

Persistent memory for AI agents. Hosted MCP server with capsule-scoped key/value storage, tags, TTL expiration, bulk ops, and RBAC.

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

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

M1K3

Round-Tower

Local AI agent for your Mac with a built-in MCP server: 18 tools for your notes and PDFs, a temporal memory graph, an on-device LLM and a neural voice. No account, no telemetry. No data centers required.

7
広告掲載