About Tool Poisoning
Tool Poisoning is a project for experimenting with and analyzing tool poisoning techniques in a controlled environment. It runs as a Python server and includes instructions for stdio transport when the server and client share a machine.
Key features
- 01Experiment with tool poisoning techniques
- 02Analyze techniques in a controlled environment
- 03Run as a Python server
- 04Use stdio transport on the same machine
Use cases
- 01Conduct controlled tool poisoning experiments
- 02Analyze tool poisoning behavior locally
MCP support
The project is described as an MCP server for running tool poisoning experiments; it can use stdio transport when the client and server run on the same machine.
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 READMETool Poisoning
Description
This project is focused on experimenting with and analyzing tool poisoning techniques in a controlled environment.
Setup
- Clone the repository:
git clone <repository-url> - Navigate to the project directory:
cd MCP Server/tool_poisoning - Install dependencies:
pip install -r requirements.txt
Usage
- Run the server:
python tool_poisoning.py - If the server and client are on the same machine, use the
stdiotransport:uv run tool_poisoning.py - Follow the on-screen instructions to execute specific experiments.
Contributing
Feel free to submit issues or pull requests to improve the project.
License
This project is licensed under the MIT License.
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.