IntentProbe

mcpware/IntentProbe

★ 7 stars Python AI/LLM Updated 4d ago

Activation-probe security scanner for AI agent tooling. Reads a model's internal activations to detect poisoned MCP servers, skills, and packages before install.

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": {
    "intentprobe": {
      "command": "uvx",
      "args": [
        "intentprobe"
      ]
    }
  }
}

Or install with pip: pip install intentprobe

README Excerpt

The First and Only MCP scanner that reads what the model understood, not what the text says. <a href="https://github.com/mcpware/IntentProbe/stargazers"><img src="https://img.shields.io/github/stars/mcpware/IntentProbe?style=social" alt="Stars" /></a>

Topics

activation-probingagent-securityai-agent-securityai-securityclaude-codeguardrailsinterpretabilityllm-securitylocal-firstmcpmcp-securitymcp-servermodel-context-protocolopen-sourceprompt-injection

IntentProbe

Quick Install

README Excerpt

Topics

Related AI/LLM Servers