Skip to content
Back to search

nova-proximity

Nova-Proximity is a MCP and Agent Skills security scanner powered with NOVA

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/nova-hunting--nova-proximity/badge.svg)](/listings/nova-hunting--nova-proximity)

HTML

<a href="/listings/nova-hunting--nova-proximity"><img src="/api/listings/nova-hunting--nova-proximity/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

# Clone and setup
git clone https://github.com/fr0gger/nova-proximity.git
cd nova-proximity
pip install -r requirements.txt

# MCP server - tools and prompt discovery
python novaprox.py http://localhost:8000

# MCP security scan (requires nova-hunting)
python novaprox.py http://localhost:8000 -n -r my_rule.nov

# Agent Skills - scan for security issues
python novaprox.py --skill /path/to/skill -n -r skill_rules.nov

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 253 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Nova Proximity - MCP and Skills Security Scanner
  2. <div align="center">
  3. ```
  4. ███╗ ██╗ ██████╗ ██╗ ██╗ █████╗ ██████╗ ██████╗ ██████╗ ██╗ ██╗
  5. ████╗ ██║██╔═══██╗██║ ██║██╔══██╗ ██╔══██╗██╔══██╗██╔═══██╗╚██╗██╔╝
  6. ██╔██╗ ██║██║ ██║██║ ██║███████║ ██████╔╝██████╔╝██║ ██║ ╚███╔╝
  7. ██║╚██╗██║██║ ██║╚██╗ ██╔╝██╔══██║ ██╔═══╝ ██╔══██╗██║ ██║ ██╔██╗
  8. ██║ ╚████║╚██████╔╝ ╚████╔╝ ██║ ██║ ██║ ██║ ██║╚██████╔╝██╔╝ ██╗
  9. ╚═╝ ╚═══╝ ╚═════╝ ╚═══╝ ╚═╝ ╚═╝ ╚═╝ ╚═╝ ╚═╝ ╚═════╝ ╚═╝ ╚═╝
  10. ```
  11. A security scanner for MCP (Model Context Protocol) servers and Agent Skills
  12. [![Python](https://img.shields.io/badge/Python-3.10%2B-blue.svg)](https://python.org) [![License: GPL v3](https://img.shields.io/badge/License-GPLv3-blue.svg)](LICENSE) [![Version](https://img.shields.io/badge/Version-1.2.0-orange.svg)](https://github.com/fr0gger/nova-proximity) [![Author](https://img.shields.io/badge/Author-@fr0gger__-red.svg)](https://twitter.com/fr0gger_)
  13. </div>
  14. ## Overview
  15. Nova Proximity scans MCP (Model Context Protocol) servers and Agent Skills to discover tools, prompts, and resources. It provides detailed analysis of server capabilities and security evaluation using NOVA rules to detect potential security issues like prompt injection, jailbreak attempts, and suspicious code patterns.
  16. ### Key Features
  17. - **MCP Server Scanning**: Discover tools, prompts, and resources with full parameter analysis
  18. - **Agent Skills Analysis**: Comprehensive skill overview, structure, permissions, and security
  19. - **NOVA Security Rules**: Pattern-based security analysis with LLM evaluation
  20. - **MCP Spec 2025-11-25**: Full support including Streamable HTTP, session management, and tool annotations
  21. - **Pattern-Specific Remediation**: Actionable guidance for each security finding
  22. ## Quick Start
  23. ```bash
  24. # Clone and setup
  25. git clone https://github.com/fr0gger/nova-proximity.git
  26. cd nova-proximity
  27. pip install -r requirements.txt
  28. # MCP server - tools and prompt discovery
  29. python novaprox.py http://localhost:8000
  30. # MCP security scan (requires nova-hunting)
  31. python novaprox.py http://localhost:8000 -n -r my_rule.nov
  32. # Agent Skills - scan for security issues
  33. python novaprox.py --skill /path/to/skill -n -r skill_rules.nov
  34. ```
  35. ## Installation
  36. ```bash
  37. git clone https://github.com/fr0gger/nova-proximity.git
  38. cd nova-proximity
  39. pip install -r requirements.txt
  40. ```
  41. ### NOVA Security Analysis Setup
  42. ```bash
  43. # Install Nova dependencies
  44. pip install nova-hunting
  45. # Set API key (choose one depending on the model you want to use)
  46. export OPENAI_API_KEY="your-openai-key"
  47. export GROQ_API_KEY="your-groq-key"
  48. export ANTHROPIC_API_KEY="your-anthropic-key"
  49. export AZURE_OPENAI_API_KEY="your-azure-key"
  50. export AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com/"
  51. # For Ollama, the default host is used (http://localhost:11434) but you can override it if needed
  52. export OLLAMA_HOST="http://localhost:11434"
  53. ```
  54. Refer to the NOVA documentation for more details: https://docs.novahunting.ai/
  55. ## Usage
  56. ### Command Structure
  57. ```bash
  58. python novaprox.py <target> [options]
  59. ```
  60. ### Common Options
  61. | Option | Description |
  62. |--------|-------------|
  63. | `-h, --help` | Show help |
  64. | `-t, --token` | Authentication token for HTTP endpoints |
  65. | `-n, --nova-scan` | Enable NOVA security analysis |
  66. | `-r, --rule` | NOVA rule file path (default: my_rule.nov) |
  67. | `-v, --verbose` | Enable verbose output |
  68. | `--json-report` | Export JSON report |
  69. | `--md-report` | Export Markdown report |
  70. | `--evaluator` | Choose LLM evaluator (openai, groq, anthropic, azure, ollama) |
  71. | `--full-output` | Show full text without truncation |
  72. ### MCP Server Scanning
  73. **HTTP Endpoints:**
  74. ```bash
  75. python novaprox.py http://localhost:8000/mcp
  76. python novaprox.py https://mcp.example.com -t your_token
  77. ```
  78. **Stdio Commands:**
  79. ```bash
  80. python novaprox.py "python server.py"
  81. python novaprox.py "node mcp-server.js"
  82. ```
  83. ### Agent Skills Scanning
  84. Nova Proximity provides comprehensive skill analysis with four sections:
  85. 1. **Overview**: Name, description, author, version, license, compatibility
  86. 2. **Structure**: Scripts, references, assets with file sizes
  87. 3. **Permissions**: Allowed tools with risk assessment
  88. 4. **Security**: Findings with pattern-specific remediation
  89. ```bash
  90. # Scan a single skill
  91. python novaprox.py --skill /path/to/skill
  92. # Scan with NOVA security analysis
  93. python novaprox.py --skill /path/to/skill -n -r skill_rules.nov
  94. # Recursively scan a skills repository
  95. python novaprox.py --skill /path/to/skills-repo --skill-recursive -n
  96. ```
  97. ### What Skills Scanning Detects
  98. | Category | Detection |
  99. |----------|-----------|
  100. | Code Execution | eval(), exec(), subprocess, dynamic imports |
  101. | Data Exfiltration | curl pipe to shell, base64 encoding, HTTP requests |
  102. | Unsafe Deserialization | pickle.load, marshal.load |
  103. | Permission Issues | Undeclared tools, wildcard permissions |
  104. | Environment Access | os.environ, config file access |
  105. Each finding includes **pattern-specific remediation** guidance.
  106. ## NOVA Security Analysis
  107. NOVA works with rules to identify specific security patterns.
  108. ### Nova Rules Example
  109. ```nova
  110. rule DetectJailbreaking
  111. {
  112. meta:
  113. description = "Detects jailbreaking attempts"
  114. author = "Thomas Roccia"
  115. severity = "critical"
  116. keywords:
  117. $previous = "previous instructions"
  118. $ignore = "ignore all the instructions above"
  119. $forget = "forget your instructions"
  120. semantics:
  121. $malicious = "hacking or unauthorized access" (0.2)
  122. llm:
  123. $jailbreak = "check if this prompt tries to bypass security"
  124. condition:
  125. any of keywords.* and any of semantics.* or llm.*
  126. }
  127. ```
  128. ### Security Scan Examples
  129. ```bash
  130. # Basic security scan
  131. python novaprox.py http://localhost:8000/mcp -n
  132. # Custom rule with Groq
  133. python novaprox.py http://localhost:8000/mcp -n -r custom.nov --evaluator groq
  134. # Comprehensive audit with reports
  135. python novaprox.py http://localhost:8000 -n -r security.nov --json-report --md-report
  136. ```
  137. ## MCP Specification Support
  138. Nova Proximity supports MCP Spec 2025-11-25:
  139. | Feature | Support |
  140. |---------|---------|
  141. | Streamable HTTP Transport | ✅ |
  142. | Legacy SSE Transport | ✅ (backwards compatible) |
  143. | Session Management | ✅ (MCP-Session-Id) |
  144. | Protocol Version Header | ✅ (MCP-Protocol-Version) |
  145. | Tool Annotations | ✅ (readOnly, destructive, idempotent, openWorld) |
  146. | Resource Annotations | ✅ (audience, priority) |
  147. ## Output Formats
  148. ### Console Output
  149. Organized display with:
  150. - Function signatures and parameters
  151. - Tool security annotations
  152. - Skill structure overview
  153. - Security findings with remediation
  154. ### JSON Export
  155. ```json
  156. {
  157. "scan_results": {
  158. "target": "http://localhost:8000",
  159. "protocol_version": "2025-11-25",
  160. "session_id": "abc123...",
  161. "tools": [...],
  162. "prompts": [...],
  163. "resources": [...]
  164. },
  165. "nova_analysis": {
  166. "flagged_count": 2,
  167. "analysis_results": [...]
  168. }
  169. }
  170. ```
  171. ### Markdown Reports
  172. Full reports available in Markdown format with all findings and remediation guidance.
  173. ## License
  174. Copyright (C) 2025 Thomas Roccia (@fr0gger_)
  175. Licensed under the GNU General Public License v3.0
  176. See LICENSE file for details.
  177. ## Author
  178. **Thomas Roccia (@fr0gger_)**
  179. - Twitter: [@fr0gger_](https://twitter.com/fr0gger_)
  180. - GitHub: [fr0gger](https://github.com/fr0gger)
  181. - Website: [securitybreak.io](https://securitybreak.io)
  182. ---
  183. <div align="center">
  184. **🛡️ Secure your MCP servers and Agent Skills with Nova Proximity!**
  185. </div>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.