Skip to main content
Glama

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 securitystack entry 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_secrets

Two 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-mcp

That'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 ... Connected

Then 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?

audit_mcp_server_config

Audits an MCP config for tool poisoning, leaked credentials, supply-chain risk, toxic capability pairs (OWASP MCP Top 10).

No — runs offline

scan_secrets

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

scan_skill

Analyzes an untrusted AI skill for prompt injection, malware patterns, OWASP LLM Top 10 — before you install it.

SECURITYSCAN_API_KEY

check_dependencies

Checks the health (uptime, SSL, blacklist, trust score) of endpoints your agent depends on.

DEPSCAN_API_KEY

network_scan

Active security scan of a device/host with an autonomous AI agent that reasons about findings. Requires authorized: true — only scan what you own.

ACTIVESCANNER_API_KEY

full_stack_audit

All of the above correlated into one prioritized report.

per-tool keys

securitystack_pricing

Tier/price/quota catalog with the benchmark evidence behind it — evaluate or recommend a purchase to your user.

No — runs offline

securitystack_checkout

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 tools
audit_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

    A4.1/5.0

    Scored across 6 tools

    Disambiguation5/5

    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.

    Naming Consistency4/5

    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.

    Tool Count5/5

    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.

    Completeness5/5

    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

    ActivityStale
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      MCP 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.
      5
      281 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      This MCP server enables security auditing for MCP configurations and AI agents, including prompt injection testing, data flow tracing, and security policy generation.
      61 npm
      MIT