Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@ShieldNet MCP scan https://example.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Bring security governance to any AI agent deployment via MCP.
Track: Secure & Govern MCP | MCP_HACK//26
ShieldNet MCP is a zero-trust guardrail for AI agents. Before your agent connects to any external endpoint (API, webhook, third-party service), ShieldNet scans it and returns an ALLOW / WARN / BLOCK decision — with full findings and severity ratings.
Scan URLs for 50+ checks across 7 security modules
Governance decisions — auto-gate agent connections with ALLOW/WARN/BLOCK
Security headers audit — quick compliance check
Side-by-side comparisons — which endpoint is safer?
Session history — track all scans with grades and scores
Pre-built prompts — security audit & pre-deployment check workflows
Related MCP server: intaris
AI agents increasingly interact with external APIs and services. Without security governance:
An agent could connect to a compromised endpoint
Sensitive data could leak through misconfigured CORS
Injection attacks could manipulate agent behavior
ShieldNet acts as a security guardrail — scan first, connect later.
┌──────────┐ ┌───────────────────────┐
│ │ │ agentgateway │
│ AI Agent│──────▶│ ┌─────────────────┐ │ ┌────────═══════┐
│ (Claude, │ │ │ 🔗 ShieldNet │ │ │ External │
│ GPT, │◀──────│ │ MCP Server │──┼─────▶│ Service │
│ etc.) │ │ │ │ │ │ (target URL) │
│ │ │ │ ┌───────────┐ │ │ │ │
└──────────┘ │ │ │ Scanners │ │ │ └───────────────┘
│ └──┼───────────┼──┘ │
│ │ │ │
│ ┌──▼──┐ ┌───────▼──┐ │
│ │Headers│ │Injection │ │
│ │ TLS │ │Info Disc │ │
│ │ Auth │ │Misconfig │ │
│ │Rate │ │ │ │
│ │Limit │ │ │ │
│ └──────┘ └──────────┘ │
│ ALLOW / WARN / BLOCK │
└────────────────────────┘Flow:
AI agent requests external connection
agentgateway routes to ShieldNet MCP
ShieldNet runs 7 scanner modules in parallel
Returns ALLOW/WARN/BLOCK + detailed findings
agentgateway enforces the decision
# | Module | What It Checks |
1 |
| HSTS, CSP, X-Frame-Options, Cookie flags, CORS wildcards, info disclosure |
2 |
| Reflected XSS, SQLi, SSTI, Command Injection, Path Traversal, SSRF, Open Redirect |
3 |
| 25 sensitive paths (.env, .git, package.json, swagger, backups, server-status) |
4 |
| HTTP vs HTTPS, SSL/TLS redirect enforcement |
5 |
| JWT exposure, JWT |
6 |
| CORS origin reflection, TRACE method, version disclosure in error pages |
7 |
| 20-request burst test (aggressive mode only) |
git clone https://github.com/hhhashexe/shieldnet-mcp.git
cd shieldnet-mcp
npm installbash demo.sh https://example.comThis launches the MCP server, discovers available tools via tools/list, runs a live scan, and pretty-prints the results with colors. 🤙
npm test75 integration tests covering all 6 MCP tools, 6 tools + 3 resources + 2 prompts.
Add to your claude_desktop_config.json:
{
"mcpServers": {
"shieldnet": {
"command": "node",
"args": ["/path/to/shieldnet-mcp/src/index.js"]
}
}
}targets:
- name: shieldnet-security
provider:
type: mcp
config:
command: node
args: ["src/index.js"]See agentgateway.yaml for full configuration.
echo '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"my-agent","version":"0.1"}}}
{"jsonrpc":"2.0","method":"notifications/initialized"}
{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"scan_url","arguments":{"url":"https://example.com"}}}' | node src/index.jsTool | Description |
Comprehensive scan — 7 modules, 50+ checks, A-F grade | |
Scan + governance decision (ALLOW/WARN/BLOCK) with confidence score | |
Quick security headers audit — PASS/WARN/FAIL verdict | |
Session scan history with grades | |
Side-by-side comparison of two URLs | |
View policy or evaluate a score against thresholds |
Resource | Description |
| Full attack vector database |
| Session scan history |
| ALLOW/WARN/BLOCK thresholds |
Prompt | Description |
| Full audit with executive report |
| Gate check before deployment |
ShieldNet makes ALLOW/WARN/BLOCK decisions based on:
ALLOW → Score ≥ 70, no critical findings
WARN → Score 50-69, or high-severity findings
BLOCK → Score < 50, or any critical vulnerabilitiesShieldNet has been used in production security audits:
3 CVEs discovered and responsibly disclosed
PayLock.xyz audit: 36 verified findings (4 Critical, 17 High)
Published on npm as shieldnet (v0.3.2)
MIT — see LICENSE
Security governance gate: scan a URL and return an ALLOW/WARN/BLOCK decision with confidence score. Use as a guardrail before an AI agent connects to any external service.
Inputs: url (required), context.
Quick security headers audit — checks HSTS, CSP, CORS, X-Frame-Options, cookie flags, and more.
Inputs: url (required).
Compare security posture of two URLs side by side — useful for evaluating which endpoint is safer.
Inputs: url1 (required), url2 (required).
View the security governance policy or evaluate a score against ALLOW/WARN/BLOCK thresholds.
Inputs: score, action.
View history of security scans performed in this session with grades and scores.
Inputs: limit.
Run a comprehensive security scan on a URL. Checks 7 modules: security headers, injection (XSS/SQLi/SSTI/command injection/path traversal), CORS, info disclosure (25 sensitive paths), TLS, authentication issues, and misconfigurations. Returns findings with severity ratings and a security grade (A-F). Use 'aggressive' mode to also test rate limiting.
Inputs: url (required), mode.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 6 tools
scan_url and assess_risk both scan a URL and could be confused, though assess_risk explicitly returns a governance decision. check_headers overlaps heavily with the headers module inside scan_url, creating ambiguity about which tool to call. Descriptions help clarify intent, but some boundaries remain fuzzy.
Most tools follow a clear verb_noun snake_case pattern: scan_url, check_headers, scan_history, compare_scans, assess_risk. governance_policy deviates by using a noun_noun name rather than a verb-led action name like view_policy, but the overall naming style is still predictable.
Six tools is a well-scoped set for a security scanning and governance server. Each tool has a distinct role within the workflow, and the count is neither bloated nor too thin.
The tool surface covers scanning, risk assessment, governance policy, history, and comparison, which are the core needs for this domain. A minor gap is that users cannot retrieve detailed findings from a past scan, only grades and scores, but agents can work around this by re-scanning.
Zero-trust gateway for AI agents: score tool calls, verify agent cards, enforce policy, audit.
Security scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.
Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.
Pay-per-call cybersecurity for AI agents: vuln scans, threat intel, compliance, code security.
