astafford8488/agentaegis-mcp

šŸ”’ Security🟢 Verified Active
0 Views
0 Installs

šŸ“‡ ā˜ļø - Security & trust layer for AI agents. Scan an MCP server or skill before you install it (scanmcpplugin, scanskill) — flags exfiltration, prompt-injection sinks, dangerous capabilities, install hooks and obfuscation → PROCEED/CAUTION/BLOCK. Plus vetendpoint (endpoint safety verdict before an agent calls or pays it) and 25 more tools: vuln scans, threat intel, compliance (SOC 2/ISO 27001/HIPAA), code security (SAST/secret/dependency), identity — 28 total. Per-call billing via API key or x402 USDC on Base; free discovery tier.

Quick Install

One-Click IDE Configuration
claude_desktop_config.json
{
  "mcpServers": {
    "astafford8488-agentaegis-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "astafford8488-agentaegis-mcp"
      ]
    }
  }
}
Or

Using an AI coding agent (Claude Code, Cursor, etc.)? Copy a ready-made prompt that tells it to fetch the setup instructions and install this server for you.

Documentation Overview

AgentAegis MCP Server

Glama score

Every cybersecurity service, callable by any AI agent, billed per use.

AgentAegis is an MCP server that lets AI agents perform cybersecurity operations on demand — from compliance checks to vulnerability scans to code security analysis. It wraps best-in-class open-source scanning engines (nmap, Nuclei, sslyze, Semgrep, trufflehog, trivy) in clean, agent-discoverable tool definitions with structured inputs and outputs.

Phase 2 ships: HTTP transport for remote deployment, x402 micropayments, API key auth with monthly limits, Supabase persistence, webhooks, ISO 27001 + HIPAA frameworks, Railway deploy config, and a full test suite.

Quick Start

Local (stdio for Claude Desktop)

git clone https://github.com/astafford8488/agentaegis-mcp.git
cd agentaegis-mcp
pnpm install
cp .env.example .env  # add API keys
pnpm build

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "agentaegis": {
      "command": "node",
      "args": ["/path/to/agentaegis-mcp/dist/index.js"],
      "env": {
        "NVD_API_KEY": "...",
        "ABUSEIPDB_API_KEY": "...",
        "OTX_API_KEY": "...",
        "ABUSECH_API_KEY": "...",
        "HIBP_API_KEY": "..."
      }
    }
  }
}

Remote (HTTP, for agent platforms)

# Local dev
pnpm dev:http

# Production via Docker
docker compose -f docker/docker-compose.yml up -d

# Production via Railway
railway up

Connect from any MCP-aware agent:

POST https://your-host/mcp
Authorization: Bearer aegis_<your-api-key>

Architecture

ā”Œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”
│         AI Agent (Claude, custom MCP client)            │
ā””ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”¬ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”¬ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”˜
                 │ stdio                 │ HTTP
                 │                       │
ā”Œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā–¼ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”  ā”Œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā–¼ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”
│   stdio entry (index.ts)   │  │  HTTP entry (http-server)│
ā””ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”¬ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”˜  ā””ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”¬ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”˜
                 │                       │
                 │      ā”Œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”“ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”
                 │      │  Auth Gate                   │
                 │      │  - API key (DB-backed)       │
                 │      │  - x402 micropayment         │
                 │      ā””ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”¬ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”˜
                 │                    │
ā”Œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā–¼ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā–¼ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”
│              MCP Server (server.ts)                          │
│              20 Tool Handlers                                │
ā”œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”¬ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”¤
│  Engine Wrappers         │  External APIs                  │
│  nmap, Nuclei, sslyze,   │  NVD, AbuseIPDB, AlienVault OTX + abuse.ch,    │
│  Semgrep, trufflehog,    │  HIBP, Shodan                   │
│  trivy                   │                                  │
ā”œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”“ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”¤
│  Sandbox    │ Rate Limit │ Target Validation │ Logging     │
ā””ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”˜
                            │
                  ā”Œā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā–¼ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”
                  │  Supabase          │
                  │  - customers       │
                  │  - api_keys        │
                  │  - scan_jobs       │
                  │  - usage_log       │
                  │  - webhooks        │
                  ā””ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”€ā”˜

HTTP API (Phase 2)

EndpointMethodAuthDescription
/healthGETNoneHealth check
/pricingGETNoneTool catalog with prices
/v1/customersPOSTNoneCreate customer account
/v1/customers/:id/api-keysPOSTNoneIssue an API key
/v1/customers/:id/usageGETAPI keyUsage statistics
/v1/jobs/:jobIdGETAPI keyAsync scan job status
/mcpPOSTAPI key OR x402MCP Streamable HTTP transport

Payment Flow

Option 1: API Key — Customer registers, gets a key, pays via prepaid balance or invoice. Each tool call deducts from the monthly budget.

curl -X POST https://api.agentaegis.org/v1/customers \
  -H "Content-Type: application/json" \
  -d '{"email":"you@company.com","name":"Your Name"}'

curl -X POST https://api.agentaegis.org/v1/customers/<id>/api-keys \
  -H "Content-Type: application/json" \
  -d '{"name":"production","monthly_limit_usd":100}'

Option 2: x402 Micropayment — No signup. Each tool call settles on-chain via USDC. The server returns 402 Payment Required with payment requirements; the client signs and retries with X-PAYMENT header.

Tool Catalog (20 tools)

ToolCategoryDescriptionPrice
compliance_framework_checkComplianceSOC 2, ISO 27001, HIPAA, PCI-DSS, NIST CSF assessment$0.50
evidence_collectComplianceEvidence collection plans for audit controls$0.25
control_gap_analysisCompliancePrioritized remediation roadmap$0.50
audit_report_generateComplianceAudit-ready compliance reports$1.00
policy_generateComplianceTailored security policy documents$0.50
vuln_scan_networkVuln MgmtNetwork port and vulnerability scan$1.00
vuln_scan_web_appVuln MgmtOWASP Top 10 web app scan$1.50
vuln_prioritizeVuln MgmtRisk-based vulnerability prioritization$0.25
cve_lookupVuln MgmtCVE details, CVSS, KEV status$0.10
ssl_tls_auditVuln MgmtSSL/TLS configuration audit$0.25
sast_scanCode SecurityStatic security analysis$1.00
secret_scanCode SecurityHardcoded secret detection$0.50
dependency_auditCode SecurityDependency vulnerability scan$0.50
incident_triageBlue TeamIncident classification & response plan$0.75
threat_intel_lookupBlue TeamIOC reputation lookup$0.25
dns_security_checkBlue TeamDNS security audit$0.25
email_security_auditBlue TeamEmail security configuration audit$0.50
access_reviewIdentityAccess privilege audit$0.50
mfa_auditIdentityMFA coverage assessment$0.25
credential_checkOffensiveBreach database lookup$0.50

Compliance Frameworks Supported

  • SOC 2 Type II — Full Trust Services Criteria (35 controls)
  • ISO 27001:2022 — All 4 Annex A control groups (93 controls)
  • HIPAA Security Rule — Administrative, physical, and technical safeguards (43 controls)
  • NIST CSF 2.0 — All 6 functions with categories
  • PCI DSS v4.0 — All 12 requirements with detailed controls (full evaluation logic)

Development

pnpm install        # Install dependencies
pnpm dev            # stdio mode (for Claude Desktop)
pnpm dev:http       # HTTP mode (with Streamable HTTP transport)
pnpm build          # Build for production
pnpm test           # Run vitest test suite (46 tests)

Deployment

Railway (Recommended)

railway login
railway init
railway up

Required env vars (set in Railway dashboard):

  • SUPABASE_URL, SUPABASE_SERVICE_KEY
  • X402_PAYEE_ADDRESS (your wallet)
  • NVD_API_KEY, ABUSEIPDB_API_KEY, OTX_API_KEY, ABUSECH_API_KEY, HIBP_API_KEY

Database setup

Run the migration in your Supabase SQL editor:

cat supabase/migrations/001_initial_schema.sql

Security Policy

  • Target validation: Only public IPs and registered domains. Private/reserved ranges blocked.
  • Scan isolation: Each scan runs in an isolated process with temp directory cleanup.
  • Code safety: Repos cloned shallow (depth=1), max 500MB, 5-minute timeout, no execution.
  • Secret redaction: Full secret values never returned — first 4 and last 4 characters only.
  • Rate limiting: Per API key AND per target. Max 5 concurrent scans, 10/hour per target.
  • Audit logging: All tool calls logged to usage_log (90-day retention).
  • API key hashing: Keys stored as SHA-256 hashes; raw keys never stored.

Responsible Use

AgentAegis scanning tools must only be used against systems you own or have explicit written authorization to test. By using this service, you agree that:

  1. You have authorization from the system owner to perform security testing
  2. You will not use these tools for unauthorized access or malicious purposes
  3. You accept responsibility for any scans initiated through your API key

License

MIT

Related MCP Servers

13bm/GhidraMCP

šŸ ā˜• šŸ  - MCP server for integrating Ghidra with AI assistants. This plugin enables binary analysis, providing tools for function inspection, decompilation, memory exploration, and import/export analysis via the Model Context Protocol.

šŸ”’ Security1 views
123Ergo/unphurl-mcp

šŸ“‡ ā˜ļø - URL intelligence for AI agents. 13 tools for security signals and data quality: redirect behaviour, brand impersonation detection, domain age, SSL validation, parked detection, URL structural analysis, DNS enrichment.

šŸ”’ Security0 views
82ch/MCP-Dandan

šŸ šŸ“‡ šŸ  šŸŽ 🪟 🐧 - Real-time security framework for MCP servers that detects and blocks malicious AI agent behavior by analyzing tool call patterns and intent across multiple threat detection engines.

šŸ”’ Security0 views
9hannahnine-jpg/arc-gate-mcp

šŸ - Runtime governance for MCP tool calls. Blocks prompt injection and capability abuse before tool results reach your agent.

šŸ”’ Security0 views

Engagement

Views
0
Installs
0
Upvotes
0

Views and upvotes are unique per visitor network (hashed IP). Installs count copy actions.

Status

Health: Active

Recent health check succeeded.

Last checked: 7/28/2026, 4:50:56 PM

Unclaimed listing (imported or pending owner verification). Claim it →
ā˜… Spotlight Slot

Feature Your MCP Server

Get maximum visibility for your server across our directory, search results, and detail pages.

Spotlight Your Server

Own this project?

This directory is pre-filled from public sources. Claim via GitHub README, site badge, or DNS TXT to get the verified badge and attach your website.

Claim this listing

Promote this listing

Optional paid placement. Free listings stay free forever.

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.