Agent Guard

Verified Integration

Author: @your•Category: ServerApplication

GitHub Repository

JSON-RPC 2.0

Protocol Standard

Sub-second

Execution Latency

Active

Operational Status

Client Configuration

— Connect Agent Guard to Claude Desktop or Cursor in seconds

{
  "mcpServers": {
    "agent-guard": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-agent-guard"
      ],
      "env": {}
    }
  }
}

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).

Architecture & Capabilities

System Overview

Provides robust budget control, approval workflows, and audit logging for AI agents leveraging the MCP protocol.

Indexed Date

7/21/2026

License

Open Source

Protocol Layer

stdio / SSE RPC

Frequently Asked Questions

Architecture and operational details for Agent Guard

Agent Guard offers a streamlined approval workflow where agent requests generate a unique token. Human operators can then approve or reject these requests conveniently via a dedicated web dashboard or instant notification links received through Telegram.

Related MCP Servers

Browse all servers →

@configuring

0xArchive

Provides comprehensive historical and real-time crypto market data, including orderbooks, trades, candles, and more, from Hyperliquid, HIP-3, and Lighter.xyz.

MCP Server5 FAQs

Learn more

@spawning

0xGasless

Facilitates gasless blockchain transactions and interactions directly from Claude AI conversations.

MCP Server4 FAQs

Learn more

@spawning

0xGasless

Bridges Claude AI with blockchain networks, enabling gasless transactions, swaps, and transfers directly from natural language conversations.

MCP Server5 FAQs

Learn more