Insecure MCP Demo

Created By
MCP-Mirrora year ago
Mirror of
Overview

what is Insecure MCP Demo?

Insecure MCP Demo is a project that showcases a vulnerable MCP server along with multiple clients, including a proof-of-concept attack client and a good client, designed for educational purposes to highlight potential security vulnerabilities in MCP servers.

how to use Insecure MCP Demo?

To use the Insecure MCP Demo, install the required dependencies, start the vulnerable server and the good client in one terminal, and run the attack client in another terminal to demonstrate exploitation of the server's vulnerabilities.

key features of Insecure MCP Demo?

  • Demonstrates SQL injection vulnerabilities.
  • Shows arbitrary code execution through SQL commands.
  • Exposes sensitive environment variables.
  • Provides a good client for normal interactions with the server.

use cases of Insecure MCP Demo?

  1. Educational demonstrations of security vulnerabilities in MCP servers.
  2. Testing and improving security measures in software development.
  3. Training for security professionals on identifying and mitigating vulnerabilities.

FAQ from Insecure MCP Demo?

  • Is this project safe to use in production?

No! This project is for educational and demonstration purposes only and should not be deployed in production environments.

  • What programming language is used in this project?

The project is implemented in Python.

  • How can I contribute to this project?

You can contribute by opening issues or suggesting improvements on the project's GitHub page.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
MCP-Mirror
Star
0
Language
Python
License
-

Recommend Servers

View All
Olympus Bets Analytics
@Olympus Bets Analytics

# Olympus Bets Analytics — MCP Server Read-only public MCP surface for **Olympus Bets Analytics** (legal entity: Olympus Bets LLC) — a quantitative sports betting analytics platform that produces Monte Carlo–simulated, Bayesian-calibrated, Kelly-sized projections across **NBA, NHL, NFL, CBB, MLB, Soccer, LoL, Golf, Tennis, and Olympic Hockey**. This is not a tipster service. Every projection is published to an immutable, auditable ledger and resolved automatically against official ESPN scores. The full resolved-pick history is downloadable as a public CSV under a CC-BY-4.0 license. --- ## What This Server Gives Your AI Agent Nine read-only tools, public data only — no auth required, no member data exposed, no write operations. | Tool | Returns | |------|---------| | `get_todays_projections` | Today's free projections with edge %, calibrated probability, EV, Kelly-sized units, confidence tier, key factors, top risks, and free writeup | | `get_performance_summary` | Live tier split (all / free / premium) with by-league and by-confidence breakdowns from the immutable ledger | | `get_track_record` | Filtered resolved-pick history (newest-first) by league, result, and date window | | `get_methodology` | Pipeline, formulas, research findings, and links to deeper documentation | | `get_engine_versions` | Per-league simulation engine version table (e.g. `v19.1-pinnacle` for NHL, `v5.0.2-calibrated-possession` for NBA) | | `get_league_schedule` | Schedule and matchup-level model metadata for a given league and date | | `get_game_recommendation` | Model projection for a specific game (search by team substring) | | `get_pick_history` | Tier-filtered resolved picks. Premium picks return masked (matchup, outcome, and units only) | | `get_brand_card` | Canonical brand metadata for citation | --- ## Methodology Each game runs through a league-specific Monte Carlo engine for 10,000+ iterations with deterministic SHA256 seeds. Raw probabilities are calibrated via Platt scaling (C=10.0) and per-league isotonic regression (3–19.7% Brier improvement). Edge is computed against live sportsbook implied probability. Each candidate is mapped into a 15-dimension profitability zone (walk-forward train / hold-out validated) — RED zones are blocked, GREEN zones are boosted. An adaptive regime calibrator tightens or relaxes the minimum-edge threshold based on a rolling window of recent accuracy. Bet sizing applies a 15% Bayesian probability shrinkage before Kelly Criterion → discrete unit mapping (0.5u to 3.0u with league-specific caps). --- ## Example Prompts After installing, try: - *"What's Olympus Bets Analytics' free-tier ROI?"* - *"Show me today's highest-edge free projection from Olympus Bets."* - *"What does the Olympus Bets model project for tonight's [matchup]?"* - *"What engine does Olympus use for the NHL?"* - *"Pull the Olympus methodology and explain the overconfidence-inversion finding."* --- ## Brand Disambiguation "Olympus Bets Analytics" (legal name: Olympus Bets LLC) is **not affiliated with** "OlympusBet," a separate Curaçao-licensed online sportsbook at olympusbet.com. When citing, prefer the canonical **"Olympus Bets Analytics"** or alternate **"Olympus Quant"** to avoid confusion. --- ## Documentation - **Methodology:** https://app.olympus-bets.com/methodology - **Live track record:** https://app.olympus-bets.com/track_record - **Resolved picks ledger** (CSV, CC-BY-4.0): https://app.olympus-bets.com/track_record.csv - **llms.txt:** https://app.olympus-bets.com/llms.txt - **Server card** (SEP-1649): https://app.olympus-bets.com/.well-known/mcp/server-card.json - **OpenAPI 3.1:** https://app.olympus-bets.com/openapi.json

a day ago