GenPark Prompt Injection Canary Leak Sentinel
LocalAbout GenPark Prompt Injection Canary Leak Sentinel
A Python MCP server that generates HMAC-signed, invisible zero-width canary tokens and audits outputs for leaked tokens. It is designed for LLM guardrail workflows and uses only the Python 3 standard library.
Key features
- 01HMAC-signed canary token generation
- 02Invisible zero-width tokens
- 03Output leak auditing
- 04Python 3 standard library implementation
Use cases
- 01Embedding canary tokens in prompts or content
- 02Checking LLM responses for leaked canaries
- 03Auditing outputs in guardrail workflows
MCP support
Exposes canary token generation and output leak auditing to MCP clients. The README shows configuration for Claude Desktop and Cursor.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEgenpark-prompt-injection-canary-leak-sentinel-skill
HMAC-signed zero-width invisible canary token generator and output response leak auditor for LLM guardrails
Quick Installation & MCP Integration
Add to your Claude Desktop or Cursor configuration:
{
"mcpServers": {
"genpark-prompt-injection-canary-leak-sentinel-skill": {
"command": "python",
"args": ["mcp_server.py"]
}
}
}
Zero Dependencies
Implemented entirely in Python 3 standard library.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.