# AI Security Scanner MCP - Cloud Edition
World's first comprehensive agentic AI security scanner with 27 specialized
agents covering 100% OWASP ASI + LLM vulnerabilities. This thin client
connects to our secure cloud infrastructure where all scanning happens.
## 🏗️ Architecture
This package is a **lightweight cloud proxy** (~50KB) that connects Claude Code
to our cloud-hosted security scanning infrastructure. All 27 security agents
run in our secure Google Cloud environment, not on your local machine.
**Benefits of Cloud Architecture**:
- Always up-to-date security rules
- No local compute resources needed
- Proprietary agent logic protected
- Consistent scanning environment
- Sub-second scan execution
## 🚀 Quick Start
### Step 1: Get Your API Key
1. Visit [https://app.ai-threat-scanner.com/dashboard/api-keys](https://app.ai-threat-scanner.com/dashboard/api-keys)
2. Sign up for free account
3. Generate new API key
4. Copy your key (format: `ciso_live_abc123xyz`)
### Step 2: Install Thin Client
```bash
claude mcp add ai-security-scanner \
-e AI_SECURITY_API_KEY=ciso_live_abc123xyz \
-- uvx ai-security-mcp
```
Replace `ciso_live_abc123xyz` with your actual API key.
### Step 3: Start Scanning
Open Claude Code and ask:
```
Scan this repository for AI security vulnerabilities
```
The thin client will connect to our cloud infrastructure, execute all 27
security agents, and return comprehensive vulnerability findings.
## 📊 What You Get
### 27 Cloud-Hosted Security Agents
**OWASP ASI (17 agents)**: Memory Poisoning, Tool Misuse, Privilege Compromise,
Resource Overload, Cascading Hallucination, Intent Breaking, Misaligned Behaviors,
Repudiation, Identity Spoofing, Overwhelming HITL, Unexpected RCE, Agent
Communication Poisoning, Rogue Agents, Human Attacks, Human Manipulation,
Insecure Protocol, Supply Chain
**OWASP LLM Top 10 (10 agents)**: Prompt Injection, Insecure Output Handling,
Training Data Poisoning, Model DoS, Supply Chain, Information Disclosure,
Insecure Plugin Design, Excessive Agency, Overreliance, Model Theft
## 🔒 Security & Privacy
**Cloud Processing**: Your code is analyzed in our secure Google Cloud
infrastructure with enterprise-grade security controls.
**Data Handling**:
- Code analyzed in isolated containers
- Results returned via encrypted HTTPS
- No permanent storage of your code
- Scan metadata tracked for quota management
**Authentication**: API keys use secure Bearer token authentication with
per-user quota tracking and access control.
## 📖 Usage Examples
### Basic Repository Scan
```
Scan this repository for agentic AI vulnerabilities
```
### Check Specific Files
```
Use the AI Security Scanner to check these files for prompt injection:
- src/prompts.py
- src/llm_integration.py
```
### Get Scan History
```
Show my recent AI security scans
```
## 🛠️ Troubleshooting
### "API Key Required" Error
You need to set your API key. Get it from:
https://app.ai-threat-scanner.com/dashboard/api-keys
Then reconfigure:
```bash
claude mcp remove ai-security-scanner
claude mcp add ai-security-scanner \
-e AI_SECURITY_API_KEY=your_actual_key \
-- uvx ai-security-mcp
```
### "Connection Failed" Error
Check cloud service status:
```bash
curl https://ai-security-mcp-fastmcp-production-722116092626.us-central1.run.app/health
```
If service is down, check status page: https://status.ai-threat-scanner.com
### "Quota Exceeded" Error
You've reached your scan limit. View usage at:
https://app.ai-threat-scanner.com/dashboard/usage
Upgrade your plan or wait for quota reset.
## 💰 Pricing
- **Free Tier**: 10 scans/day, 100 scans/month
- **Pro Tier**: 100 scans/day, unlimited monthly
- **Enterprise**: Custom quotas and dedicated support
View pricing: https://ai-threat-scanner.com/pricing
## 📚 Documentation
- **Dashboard**: https://app.ai-threat-scanner.com
- **Full Documentation**: https://ai-threat-scanner.com/docs
- **OWASP ASI Specification**: https://owasp.org/www-project-ai-security-and-privacy-guide/
- **Bug Reports**: https://github.com/ai-security-scanner/ai-security-mcp/issues
## 🏢 Architecture Details
This package contains only the thin client proxy. The actual security scanning
happens in our cloud infrastructure:
```
Your Machine Cloud Infrastructure
┌─────────────┐ ┌──────────────────────┐
│ Claude Code │─────▶│ Cloud MCP Server │
│ │ │ - 27 Security Agents │
│ Thin Client │◀─────│ - Vulnerability DB │
│ (~50KB) │ │ - Analysis Engine │
└─────────────┘ └──────────────────────┘
```
**Thin Client Responsibilities**:
- MCP protocol (stdio) with Claude Code
- HTTPS proxy to cloud server
- API key authentication
- Request/response forwarding
**Cloud Server Responsibilities**:
- API key validation
- Agent execution (all 27)
- Vulnerability analysis
- Report generation
- Quota tracking
## 📄 License
MIT License - see LICENSE file for details.
## 🔗 Links
- **Website**: https://ai-threat-scanner.com
- **Dashboard**: https://app.ai-threat-scanner.com
- **GitHub**: https://github.com/ai-security-scanner/ai-security-mcp
- **PyPI**: https://pypi.org/project/ai-security-mcp/
- **Support**: support@ai-threat-scanner.com
Raw data
{
"_id": null,
"home_page": "https://github.com/davidmatousek/CISO_Agent",
"name": "ai-security-mcp",
"maintainer": "AI Security Team",
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": "security@ai-threat-scanner.com",
"keywords": "security, ai, agentic, llm, owasp, vulnerability, scanner, mcp, claude, claude-code, agent, multi-agent, asi, prompt-injection, cybersecurity, devsecops, static-analysis, security-testing",
"author": "AI Security Team",
"author_email": "AI Security Team <security@ai-threat-scanner.com>",
"download_url": "https://files.pythonhosted.org/packages/6c/c7/cd25932c05f4dffb08411e0cb84c466a61eb9abf744721c5beff7839c16c/ai_security_mcp-1.0.26.tar.gz",
"platform": "any",
"description": "# AI Security Scanner MCP - Cloud Edition\n\nWorld's first comprehensive agentic AI security scanner with 27 specialized\nagents covering 100% OWASP ASI + LLM vulnerabilities. This thin client\nconnects to our secure cloud infrastructure where all scanning happens.\n\n## \ud83c\udfd7\ufe0f Architecture\n\nThis package is a **lightweight cloud proxy** (~50KB) that connects Claude Code\nto our cloud-hosted security scanning infrastructure. All 27 security agents\nrun in our secure Google Cloud environment, not on your local machine.\n\n**Benefits of Cloud Architecture**:\n- Always up-to-date security rules\n- No local compute resources needed\n- Proprietary agent logic protected\n- Consistent scanning environment\n- Sub-second scan execution\n\n## \ud83d\ude80 Quick Start\n\n### Step 1: Get Your API Key\n\n1. Visit [https://app.ai-threat-scanner.com/dashboard/api-keys](https://app.ai-threat-scanner.com/dashboard/api-keys)\n2. Sign up for free account\n3. Generate new API key\n4. Copy your key (format: `ciso_live_abc123xyz`)\n\n### Step 2: Install Thin Client\n\n```bash\nclaude mcp add ai-security-scanner \\\n -e AI_SECURITY_API_KEY=ciso_live_abc123xyz \\\n -- uvx ai-security-mcp\n```\n\nReplace `ciso_live_abc123xyz` with your actual API key.\n\n### Step 3: Start Scanning\n\nOpen Claude Code and ask:\n```\nScan this repository for AI security vulnerabilities\n```\n\nThe thin client will connect to our cloud infrastructure, execute all 27\nsecurity agents, and return comprehensive vulnerability findings.\n\n## \ud83d\udcca What You Get\n\n### 27 Cloud-Hosted Security Agents\n\n**OWASP ASI (17 agents)**: Memory Poisoning, Tool Misuse, Privilege Compromise,\nResource Overload, Cascading Hallucination, Intent Breaking, Misaligned Behaviors,\nRepudiation, Identity Spoofing, Overwhelming HITL, Unexpected RCE, Agent\nCommunication Poisoning, Rogue Agents, Human Attacks, Human Manipulation,\nInsecure Protocol, Supply Chain\n\n**OWASP LLM Top 10 (10 agents)**: Prompt Injection, Insecure Output Handling,\nTraining Data Poisoning, Model DoS, Supply Chain, Information Disclosure,\nInsecure Plugin Design, Excessive Agency, Overreliance, Model Theft\n\n## \ud83d\udd12 Security & Privacy\n\n**Cloud Processing**: Your code is analyzed in our secure Google Cloud\ninfrastructure with enterprise-grade security controls.\n\n**Data Handling**:\n- Code analyzed in isolated containers\n- Results returned via encrypted HTTPS\n- No permanent storage of your code\n- Scan metadata tracked for quota management\n\n**Authentication**: API keys use secure Bearer token authentication with\nper-user quota tracking and access control.\n\n## \ud83d\udcd6 Usage Examples\n\n### Basic Repository Scan\n```\nScan this repository for agentic AI vulnerabilities\n```\n\n### Check Specific Files\n```\nUse the AI Security Scanner to check these files for prompt injection:\n- src/prompts.py\n- src/llm_integration.py\n```\n\n### Get Scan History\n```\nShow my recent AI security scans\n```\n\n## \ud83d\udee0\ufe0f Troubleshooting\n\n### \"API Key Required\" Error\n\nYou need to set your API key. Get it from:\nhttps://app.ai-threat-scanner.com/dashboard/api-keys\n\nThen reconfigure:\n```bash\nclaude mcp remove ai-security-scanner\nclaude mcp add ai-security-scanner \\\n -e AI_SECURITY_API_KEY=your_actual_key \\\n -- uvx ai-security-mcp\n```\n\n### \"Connection Failed\" Error\n\nCheck cloud service status:\n```bash\ncurl https://ai-security-mcp-fastmcp-production-722116092626.us-central1.run.app/health\n```\n\nIf service is down, check status page: https://status.ai-threat-scanner.com\n\n### \"Quota Exceeded\" Error\n\nYou've reached your scan limit. View usage at:\nhttps://app.ai-threat-scanner.com/dashboard/usage\n\nUpgrade your plan or wait for quota reset.\n\n## \ud83d\udcb0 Pricing\n\n- **Free Tier**: 10 scans/day, 100 scans/month\n- **Pro Tier**: 100 scans/day, unlimited monthly\n- **Enterprise**: Custom quotas and dedicated support\n\nView pricing: https://ai-threat-scanner.com/pricing\n\n## \ud83d\udcda Documentation\n\n- **Dashboard**: https://app.ai-threat-scanner.com\n- **Full Documentation**: https://ai-threat-scanner.com/docs\n- **OWASP ASI Specification**: https://owasp.org/www-project-ai-security-and-privacy-guide/\n- **Bug Reports**: https://github.com/ai-security-scanner/ai-security-mcp/issues\n\n## \ud83c\udfe2 Architecture Details\n\nThis package contains only the thin client proxy. The actual security scanning\nhappens in our cloud infrastructure:\n\n```\nYour Machine Cloud Infrastructure\n\u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510 \u250c\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2510\n\u2502 Claude Code \u2502\u2500\u2500\u2500\u2500\u2500\u25b6\u2502 Cloud MCP Server \u2502\n\u2502 \u2502 \u2502 - 27 Security Agents \u2502\n\u2502 Thin Client \u2502\u25c0\u2500\u2500\u2500\u2500\u2500\u2502 - Vulnerability DB \u2502\n\u2502 (~50KB) \u2502 \u2502 - Analysis Engine \u2502\n\u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518 \u2514\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2518\n```\n\n**Thin Client Responsibilities**:\n- MCP protocol (stdio) with Claude Code\n- HTTPS proxy to cloud server\n- API key authentication\n- Request/response forwarding\n\n**Cloud Server Responsibilities**:\n- API key validation\n- Agent execution (all 27)\n- Vulnerability analysis\n- Report generation\n- Quota tracking\n\n## \ud83d\udcc4 License\n\nMIT License - see LICENSE file for details.\n\n## \ud83d\udd17 Links\n\n- **Website**: https://ai-threat-scanner.com\n- **Dashboard**: https://app.ai-threat-scanner.com\n- **GitHub**: https://github.com/ai-security-scanner/ai-security-mcp\n- **PyPI**: https://pypi.org/project/ai-security-mcp/\n- **Support**: support@ai-threat-scanner.com\n",
"bugtrack_url": null,
"license": null,
"summary": "Thin client MCP server for AI Security Scanner - connects to cloud-hosted 27 agents (100% OWASP coverage)",
"version": "1.0.26",
"project_urls": {
"Bug Reports": "https://github.com/ai-security-scanner/ai-security-mcp/issues",
"Documentation": "https://ai-threat-scanner.com/docs",
"Homepage": "https://ai-threat-scanner.com",
"Repository": "https://github.com/ai-security-scanner/ai-security-mcp"
},
"split_keywords": [
"security",
" ai",
" agentic",
" llm",
" owasp",
" vulnerability",
" scanner",
" mcp",
" claude",
" claude-code",
" agent",
" multi-agent",
" asi",
" prompt-injection",
" cybersecurity",
" devsecops",
" static-analysis",
" security-testing"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "de06c04b3a6b3ee3fa277b9d3e6c03dfad1057587693d3da5ea279c293154e93",
"md5": "47653c3622ab5dcce2314ea4a439f49c",
"sha256": "9405a6289f75a9e6cfbc34b8046543639184e1300bce8097f9365e56bc7b4cc1"
},
"downloads": -1,
"filename": "ai_security_mcp-1.0.26-py3-none-any.whl",
"has_sig": false,
"md5_digest": "47653c3622ab5dcce2314ea4a439f49c",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 8456,
"upload_time": "2025-10-22T16:50:29",
"upload_time_iso_8601": "2025-10-22T16:50:29.782514Z",
"url": "https://files.pythonhosted.org/packages/de/06/c04b3a6b3ee3fa277b9d3e6c03dfad1057587693d3da5ea279c293154e93/ai_security_mcp-1.0.26-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "6cc7cd25932c05f4dffb08411e0cb84c466a61eb9abf744721c5beff7839c16c",
"md5": "c876bb6bbaed86eae65c32e39c2b6463",
"sha256": "83d3fea00c1faf996d681992be3979c072840a219022b623bc4b9879af280272"
},
"downloads": -1,
"filename": "ai_security_mcp-1.0.26.tar.gz",
"has_sig": false,
"md5_digest": "c876bb6bbaed86eae65c32e39c2b6463",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 9407,
"upload_time": "2025-10-22T16:50:30",
"upload_time_iso_8601": "2025-10-22T16:50:30.613727Z",
"url": "https://files.pythonhosted.org/packages/6c/c7/cd25932c05f4dffb08411e0cb84c466a61eb9abf744721c5beff7839c16c/ai_security_mcp-1.0.26.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-22 16:50:30",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "davidmatousek",
"github_project": "CISO_Agent",
"github_not_found": true,
"lcname": "ai-security-mcp"
}
JSON
