MCP_TOOL_POISONING_ATTACKS

Created By
RyosukeDTomitaa year ago
Overview

What is MCP_TOOL_POISONING_ATTACKS?

MCP_TOOL_POISONING_ATTACKS is a tool designed to facilitate the execution of poisoning attacks on Model Context Protocol (MCP) servers, particularly in the context of GitHub repositories.

How to use MCP_TOOL_POISONING_ATTACKS?

To use this tool, set up your environment by installing Node.js and Docker, then configure the necessary API keys and server settings in the provided JSON files. You can run the tool either in a development container or directly using Docker commands.

Key features of MCP_TOOL_POISONING_ATTACKS?

  • Supports Node.js and Docker environments.
  • Allows configuration of multiple MCP servers.
  • Provides example configurations for GitHub integration.

Use cases of MCP_TOOL_POISONING_ATTACKS?

  1. Testing the resilience of MCP servers against poisoning attacks.
  2. Automating the creation of issues in GitHub repositories as part of the attack simulation.
  3. Evaluating the performance of different models in response to malicious inputs.

FAQ from MCP_TOOL_POISONING_ATTACKS?

  • What is a poisoning attack?

A poisoning attack involves manipulating the input data to a model to degrade its performance or to cause it to behave in an unintended manner.

  • Is this tool safe to use?

This tool is intended for research and educational purposes only. Ensure you have permission to test any servers you target.

  • Can I use this tool with any MCP server?

Yes, as long as the server is compatible with the Model Context Protocol.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
RyosukeDTomita
Star
3
Language
TypeScript
License
Unlicense license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

10 hours ago