Halberd

Builder106/Halberd

★ 0 stars Go 🤖 AI/LLM Updated today

A JSON-RPC firewall for MCP agents — inspects every tools/call between an LLM and its MCP servers, blocking argument injection and capability creep before they reach the host.

View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "halberd": {
      "command": "go",
      "args": [
        "run",
        "github.com/Builder106/Halberd@latest"
      ]
    }
  }
}

README Excerpt

<picture> <source media="(prefers-color-scheme: dark)" srcset="assets/banner-dark.svg"> <source media="(prefers-color-scheme: light)" srcset="assets/banner-light.svg"> <img alt="Halberd — a JSON-RPC firewall for MCP agents" src="assets/banner-dark.svg"> </picture> **Halberd** is a high-throughput reverse proxy that sits between an LLM agent

Topics

agentic-aiai-securitygojson-rpcllm-securitymcpmodel-context-protocolprompt-injectionreverse-proxyzero-trust

Halberd

Quick Install

README Excerpt

Topics

Related AI/LLM Servers