AgentGuard

Verified Integration

Author: @independently•Category: ServerApplication

GitHub Repository

JSON-RPC 2.0

Protocol Standard

Sub-second

Execution Latency

Active

Operational Status

Client Configuration

— Connect AgentGuard to Claude Desktop or Cursor in seconds

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

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

Architecture & Capabilities

System Overview

Ensures AI agents perform tasks as contracted by independently verifying required evidence.

Indexed Date

7/21/2026

License

Open Source

Protocol Layer

stdio / SSE RPC

Frequently Asked Questions

Architecture and operational details for AgentGuard

AgentGuard addresses the 'false progress' problem, where AI agents report task completion without actual execution. It independently verifies agent outputs against predefined contracts and evidence requirements, ensuring true accountability and reliable task execution.

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