SecurityStack MCP
SecurityStack MCP gives an AI agent eight MCP tools to secure its own environment — auditing MCP configs, redacting secrets/PII, vetting skills, checking dependencies, scanning networks, and even purchasing security tiers.
Audit an MCP client config offline for poisoning, leaked credentials, unpinned packages, insecure transport, and toxic capability pairs (
audit_mcp_server_config).Scan and redact secrets/PII (API keys, tokens, emails, credit cards, etc.) in any payload before it leaves for an LLM/API — works offline (
scan_secrets).Vet an untrusted AI skill for prompt injection, malware, and OWASP LLM Top 10 before installing (
scan_skill).Check dependency health: uptime, SSL validity, blacklist status, and a trust score (
check_dependencies).Run active network scans of a host/IP/CIDR with an AI agent loop, requiring explicit authorization (
network_scan).Run a correlated, prioritized full-stack audit combining config, dependencies, skill, network, and secret checks (
full_stack_audit).Retrieve pricing/tier/quotas with benchmark evidence (
securitystack_pricing).Open a Stripe checkout to buy a tier and get a PENDING API key that activates on payment (
securitystack_checkout).
Enables agent-native purchases by opening a Stripe checkout session for a SecurityScan tier and returning a payment URL with an API key that activates automatically upon payment.
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., "@SecurityStack MCP Audit my MCP config for security risks"
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.
SecurityScan MCP
Give your AI agent the ability to secure its own environment — one MCP config, eight tools.
Audit MCP configs for poisoning, redact secrets/PII before they leave for an LLM, vet untrusted skills, monitor dependency health, and actively scan your network. All from a single
securitystackentry in your agent's MCP config.
This is the client: the unified MCP server an AI agent (Claude CLI/Desktop, or any MCP-aware agent) installs to call the SecurityScan hosted services. The backend services themselves are hosted — you don't run them. You configure API keys and your agent gets eight tools — six security plus two sales.
Why
An AI agent has four ways to get compromised. SecurityScan covers all four:
1. What it INSTALLS → poisoned skills / MCP configs → scan_skill + audit_mcp_server_config
2. What it DEPENDS ON → a dependency goes down/rogue → check_dependencies
3. Where it's EXPOSED → open ports, default creds → network_scan (with AI agent loop)
4. What it SENDS OUT → secrets/PII leak into the LLM → scan_secretsTwo of these — audit_mcp_server_config and scan_secrets — run offline, in-process, with no API
key. They work the moment you install the server. The other four call hosted services (configure
their keys to enable them; each is skipped gracefully if unset).
Related MCP server: Mund
Install
1. Install the server
pip install securityscan-mcpThat's it — the package is on PyPI.
2. Add it to your agent
For Claude Desktop / CLI (claude_desktop_config.json or ~/.claude.json):
{
"mcpServers": {
"securityscan": {
"command": "python",
"args": ["-m", "stack.unified_mcp_server"],
"env": {
"ACTIVESCANNER_API_KEY": "ask_live_...",
"DEPSCAN_API_KEY": "dsk_live_...",
"SECURITYSCAN_API_KEY": "ss_live_...",
"SECRETSCAN_API_KEY": "ssc_..."
}
}
}
}The three offline tools (audit_mcp_server_config, scan_secrets, securitystack_pricing) need no key and work immediately.
The four hosted-service tools activate when you set their key; set only what you use.
Get a free API key (no credit card):
curl -X POST https://scan.apisecurityscan.net/v1/register -d '{}'See docs/QUICKSTART.md for the 2-minute setup.
3. Verify
claude mcp list
# securitystack ... ConnectedThen ask your agent: "Audit my MCP config for security risks" or "Scan this prompt for secrets before I send it: ..."
The eight tools
Tool | What it does | Needs a key? |
| Audits an MCP config for tool poisoning, leaked credentials, supply-chain risk, toxic capability pairs (OWASP MCP Top 10). | No — runs offline |
| Detects & redacts secrets (API keys, tokens, private keys) + PII (email, phone, SSN, credit card, IBAN) in a payload before it leaves for an LLM/API. Runs offline in-process with no key; routes to the backend if a key is set. | No — runs offline |
| Analyzes an untrusted AI skill for prompt injection, malware patterns, OWASP LLM Top 10 — before you install it. |
|
| Checks the health (uptime, SSL, blacklist, trust score) of endpoints your agent depends on. |
|
| Active security scan of a device/host with an autonomous AI agent that reasons about findings. Requires |
|
| All of the above correlated into one prioritized report. | per-tool keys |
| Tier/price/quota catalog with the benchmark evidence behind it — evaluate or recommend a purchase to your user. | No — runs offline |
| Agent-native purchase: opens a Stripe checkout for a tier and returns the payment URL plus a PENDING API key that activates automatically on payment. | No — public endpoint |
Authorization & legality
network_scan performs active scanning. You must set authorized: true to certify you own or
have permission to scan the target. Scanning without authorization may violate the CFAA (US), the
Computer Misuse Act (UK), and similar laws. See the Terms of Service.
License
Apache-2.0. See LICENSE.
Available Tools
6 toolsaudit_mcp_server_configA
Audit an MCP client configuration for security risks — works offline, no external service required. Detects: tool poisoning, hidden/coercive instructions in tool descriptions, hardcoded credentials, unpinned packages (rug-pull risk), insecure transport, and toxic capability combinations (shell + network, file-read + network).
Inputs: config_json (required). Returns: result
check_dependenciesB
Check the health of your agent's external dependencies: uptime, SSL validity, blacklist status, and a trust score 0-100 (DepScan).
Inputs: endpoints (required). Returns: result
full_stack_auditA
Complete security posture in one call: audits the MCP config, checks dependency health, analyzes an untrusted skill, scans the local network gateway, and scans any payload you're about to send out for secrets/PII — then correlates everything into a single prioritized report. Pass only what you have; each section is skipped gracefully if its input or service is missing.
Inputs: skill_url, text_to_scan, network_target, mcp_config_json, +2 more. Returns: result
network_scanA
Active security scan of a device or host with an autonomous AI agent that decides which follow-up probes to run (ActiveScanner). Only scan targets you own or have permission to test.
Inputs: target (required), authorized (required), scan_type. Returns: result
scan_secretsA
Scan a text payload (a prompt, an outbound API body, a file's contents) for secrets and PII BEFORE it leaves for an LLM or external API, and return a redacted copy. Catches the #1 real-world agent incident: secrets/PII leaking into a model's context.
WORKS OFFLINE with no API key — the detection runs in-process (pure regex
Luhn check, no network). If a SecretScan backend key IS configured, the scan is routed there instead (which also persists an audit record).
Inputs: text (required), redact. Returns: result
scan_skillA
Analyze an AI agent skill for prompt injection, malware patterns, and OWASP LLM Top 10 issues BEFORE installing it (SecurityScan).
Inputs: skill_url (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool addresses a distinct security concern: skill scanning, dependency health, network probing, MCP config auditing, and secrets/PII detection. The full_stack_audit is clearly a composite that calls the others, so there's no confusion about when to use individual tools vs. the aggregate.
Most tools follow a verb_noun pattern (scan_skill, check_dependencies, audit_mcp_server_config, scan_secrets). However, network_scan and full_stack_audit invert the order, making the pattern slightly inconsistent.
With 6 tools, the set is well-scoped for a security-focused server, covering different attack surfaces without unnecessary bloat. Each tool earns its place and the count falls comfortably within the ideal range.
The tool set covers a broad range of security checks relevant to AI agent workflows, including skills, dependencies, network, MCP configuration, and data leakage. The full_stack_audit tool aggregates all checks, providing a complete posture assessment in one call. No obvious gaps exist for the stated purpose.
Maintenance
Related MCP Connectors
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Scan AI agent skills, MCP server packages and MCP configs before you install them. Static analysis.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Related MCP Servers
- AlicenseAqualityBmaintenanceMCP server for https://oathe.ai security audits. Runtime behavioral analysis and security scanner for Ai systems. Check trust scores before installing MCP servers, plugins, or AI agent skills.5281 npm1MIT
- AlicenseNot gradedqualityBmaintenanceMCP security scanner for AI agents - detects prompt injection, secrets, PII, and vets MCP servers before installation1Apache 2.0
- FlicenseNot gradedqualityDmaintenanceMCP server for auditing AI agent permissions and access by scanning for the trifecta of credentials, injection, and reach without heavy infrastructure.-
- AlicenseNot gradedqualityCmaintenanceThis MCP server enables security auditing for MCP configurations and AI agents, including prompt injection testing, data flow tracing, and security policy generation.61 npmMIT