広告掲載
MCP.so
ログイン
C

Carapace MCP Server

@jdesl55

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

jdesl55

投稿者

FEJ

Carapace MCP Server について

Armor for your AI agent. Carapace is a local-first security system that protects autonomous AI agents from prompt injection and goal drift. It verifies actions against user-defined rules before execution, uses rotating HMAC keys that injected prompts can't forge, re-reads goals e

Carapace 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": {
    "carapace": {
      "command": "carapace-mcp",
      "args": []
    }
  }
}

Carapace MCP Server のツール

5

Security checkpoint. Validates actions against your rules, returns pass/block verdict with rotating key.

Goal journal. Returns your goals, priorities, and constraints. Detects drift by comparing agent activity against configured categories.

Action logger. Records what the agent did, flags unverified sensitive actions.

Security posture summary. Health status, action counts, key rotation timing, drift level.

Session grader. Analyzes all actions against goals, produces a scorecard with grades, highlights, and improvement insights.

概要

What is Carapace?

Carapace is a local-first security system for autonomous AI agents. It plugs into any MCP-compatible agent (OpenClaw, Claude Code, Codex, and others) and provides security verification, goal anchoring, drift detection, action logging, and session grading — all running on your machine with zero cloud dependencies.

How to use Carapace?

Install via Git and npm, then build the project. Add the server to your agent's MCP configuration (e.g., ~/.config/openclaw/mcp.json) by specifying the path to the built index.js. On first run, Carapace creates ~/.carapace/ with configuration, database, and security secret. Edit ~/.carapace/config.json by hand or use the optional Carapace Dashboard.

Key features of Carapace

  • Security checkpoint that validates actions against user-defined rules
  • Rotating cryptographic key (every 30 minutes) to prevent prompt injection hijacking
  • Goal anchoring that re-reads priorities every 15 minutes to detect drift
  • Action logger that records all agent activity and flags unverified sensitive actions
  • Session grader that produces scorecards and actionable insights for agent improvement
  • Completely local, zero cloud dependencies for core security operations

Use cases of Carapace

  • Blocking unauthorized spending, messaging, or file deletion by AI agents
  • Preventing prompt injection attacks where malicious instructions are hidden in emails or web pages
  • Keeping an agent focused on its original goals and detecting when it wanders off-task
  • Logging and reviewing every action an agent takes for audit and accountability

よくある質問

1

What problem does Carapace solve?

Carapace addresses two critical risks of autonomous AI agents: prompt injection (tricking the agent into executing unauthorized actions) and goal drift (the agent losing focus over time).

2

How does the rotating key anti-hijacking work?

Every 30 minutes, Carapace generates a cryptographic verification key using a secret that never enters the agent's context window. The real agent has the key; a prompt injection cannot forge it.

3

What are the dependencies and runtime requirements?

Carapace requires Node.js and runs on any platform where Node.js is available. It uses TypeScript, the MCP SDK, better-sqlite3 for local logging, and HMAC-SHA256 for key verification. It has zero external dependencies for core security operations.

4

Where does Carapace store data?

All data lives in `~/.carapace/` on the local machine. This includes `config.json` (security rules, goals), `logs.db` (action log), `.secret` (HMAC signing key with 600 permissions), and `insights.md` (session learnings).

5

What transport does Carapace use and how does it authenticate?

Carapace communicates over stdio via the Model Context Protocol. The HMAC secret is created with owner read/write permissions only and never enters the agent's context window or is transmitted over any network.

コメント

「その他」の他のコンテンツ

Soar Flight Booking MCP

Soar Flight Booking MCP is a remote MCP server available at https://mcp.soar.flights.

EverArt

modelcontextprotocol

Model Context Protocol Servers

88.1K
P

PickFu MCP

PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

Sequential Thinking

modelcontextprotocol

Model Context Protocol Servers

88.2K

Klarix Intelligence Engine

Klarix

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

広告掲載