offsec-mcp
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., "@offsec-mcp Find subdomains of example.com and check the main site's security headers."
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.
offsec-mcp
Offensive-security tooling for AI agents — over the Model Context Protocol.
Give Claude, Cursor, or any MCP client the ability to run reconnaissance, pull CVE intelligence, analyze JavaScript, and scan ports — only against targets you're authorized to test.
Why
Pentesters and bug-bounty hunters live in a dozen CLI tools. AI agents are great at orchestrating multi-step work — but they can't touch those tools. offsec-mcp bridges the gap: it exposes a focused set of security capabilities as MCP tools, so you can just ask —
"Enumerate subdomains of
example.com, check which are live, and tell me if any run software with a critical CVE."
— and the agent chains recon_subdomains → http_probe → cve_search for you.
Built on battle-tested logic from reconwave, cve-forge, and jsintel.
Related MCP server: wrg-mcp-server
Guardrails first
This is a dual-use tool, so authorization is enforced in code, not left to good intentions:
Passive OSINT (CT logs, DNS, RDAP, NVD, analyzing pasted JS) runs freely — it never touches the target.
Active tools (
port_scan,http_probe,security_headers) refuse to run unless the target is in your configured authorization scope. No scope → no active probing.Discovered secrets are redacted in output, never returned in full.
See SECURITY.md for the responsible-use policy.
Tools
Tool | Type | What it does |
| passive | Sub-domain enumeration from Certificate Transparency (crt.sh) |
| passive | A/AAAA/MX/NS/TXT/CNAME via DNS-over-HTTPS |
| passive | Registration data via RDAP (registrar, dates, nameservers) |
| passive | Search NVD by keyword, filter by CVSS |
| passive | Full details + references for a CVE id |
| passive* | Extract secrets, endpoints & params from JS |
| active | Status, headers & tech fingerprint of a URL |
| active | Audit security headers, grade A–F |
| active | Async TCP-connect scan of common/custom ports |
| — | Report whether an authorization scope is set |
* analyze_js is passive on pasted content; fetching a URL requires scope.
Install
Run instantly with uv — no clone needed:
uvx offsec-mcp # runs the server (stdio) — or: pip install offsec-mcpOr install from source:
git clone https://github.com/nadirzhon/offsec-mcp
cd offsec-mcp
uv pip install -e ".[dev]"Configure your MCP client
Claude Desktop / Claude Code
Add to your MCP config (see examples/claude_desktop_config.json):
{
"mcpServers": {
"offsec": {
"command": "uvx",
"args": ["offsec-mcp"],
"env": {
"OFFSEC_SCOPE": "example.com,*.staging.example.com,10.0.0.0/24"
}
}
}
}Authorization scope
Active tools only run against hosts you list. Two ways to set it:
# inline — domains, wildcards, and CIDRs
export OFFSEC_SCOPE="example.com,*.staging.example.com,10.0.0.0/24"
# or a file, one entry per line (# comments allowed)
export OFFSEC_SCOPE_FILE="./scope.txt"For a fully-owned lab you control, OFFSEC_ALLOW_ANY=1 disables the guard. NVD_API_KEY
(optional) raises NVD rate limits.
Example session
You: Find subdomains of example.com and check the main site's security headers.
Agent: → recon_subdomains("example.com") → 143 subdomains from CT logs
→ security_headers("https://example.com")
→ Grade C (60): missing CSP, Permissions-Policy.
www, api, staging, dev.example.com are live.See examples/sample_output.md for real tool output.
Development
uv pip install -e ".[dev]"
pytest # scope guard + tool logic
ruff check .Part of an AI × Security toolkit
offsec-mcp — MCP server giving AI agents offensive-security tools (recon, CVE, JS analysis) · (this repo)
specter — autonomous AI recon agent that drives those tools end-to-end
vigil — AI security review for every pull request
mcpscan — security scanner for MCP servers (tool poisoning, injection surfaces)
State of MCP Security — research: 87% of scanned MCP servers expose a medium+ hardening issue
License
MIT — see LICENSE. Published for authorized security testing, research, and education only. You are responsible for having explicit permission to test any target.
Available Tools
10 toolsanalyze_jsAnalyze JsB
Extract secrets, endpoints, and parameters from JavaScript (pasted content or a URL).
Inputs: source (required). Returns: object
cve_lookupCve LookupB
Fetch full details and references for a specific CVE id (e.g. CVE-2024-3094).
Inputs: cve_id (required). Returns: object
cve_searchCve SearchB
Search the NVD for recent CVEs by keyword, filtered by minimum CVSS score.
Inputs: keyword (required), limit, min_cvss. Returns: object
dns_lookupDns LookupB
Resolve A/AAAA/MX/NS/TXT/CNAME records for a domain (via DNS-over-HTTPS).
Inputs: domain (required). Returns: object
http_probeHttp ProbeB
Fetch a URL and report status, key headers, and detected technologies. [active — needs scope]
Inputs: url (required). Returns: object
port_scanPort ScanB
TCP-connect scan a host for open ports (defaults to common ports). [active — needs scope]
Inputs: host (required), ports. Returns: object
recon_subdomainsRecon SubdomainsA
Passively enumerate sub-domains of a domain from Certificate Transparency logs.
Inputs: domain (required). Returns: object
scope_statusScope StatusB
Report whether an authorization scope is configured for active tools.
Inputs: no named parameters. Returns: object
security_headersSecurity HeadersB
Audit a site's HTTP security headers and grade them A–F. [active — needs scope]
Inputs: url (required). Returns: object
whoisWhoisB
Look up domain registration data (registrar, dates, nameservers) via RDAP.
Inputs: domain (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Most tools have clearly distinct targets: DNS, WHOIS, subdomain enumeration, CVE search/detail, JS analysis, HTTP probing, header auditing, and port scanning. The main potential confusion is between cve_search and cve_lookup, and between http_probe and security_headers, but descriptions make the boundaries reasonably clear.
The set mixes conventions: noun_verb forms like dns_lookup, cve_search, and port_scan alongside verb_noun analyze_js, bare nouns like whois and security_headers, and the less predictable recon_subdomains. The names are readable, but there is no single consistent pattern.
Ten tools is well-scoped for an offensive-security reconnaissance server. Each tool maps to a distinct phase or resource, and none appears redundant or trivial.
The surface covers a solid recon workflow: subdomain discovery, DNS, WHOIS, CVE research, JavaScript analysis, HTTP probing, security-header auditing, and port scanning, plus scope status. Minor gaps exist, such as URL/content discovery or broader vulnerability scanning, but core workflows are represented.
Maintenance
Related MCP Connectors
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
MCP server for Pentest-Tools.com: run scans, manage findings and reports via your preffered LLM.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
The main MCP server has 10 tools, including six public, read-only CVE tools, site search and page reading. CVE results include source software/version evidence and available CISA KEV and dated FIRST EPSS data. The separate request_security_test action requires an agent key, consent and authorization. A no-account, read-only CVE-only endpoint is https://excessionlabs.ai/mcp/cve. Docs: https://excessionlabs.ai/cve-intelligence/.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceAn MCP server that exposes over 20 standard penetration testing utilities, such as Nmap, SQLMap, and OWASP ZAP, as callable tools for AI agents. It enables natural language control over complex security workflows for automated and interactive penetration testing.117-
- AlicenseNot gradedqualityAmaintenanceAn MCP server that exposes a 60+ tool security and threat-intel stack to AI agents, enabling secret scanning, Sigma rule generation, ransomware lookup, OSINT, and deep research.1MIT
- FlicenseNot gradedqualityDmaintenanceAI-powered Attack Surface Intelligence server that exposes industry-standard penetration testing tools via MCP, enabling AI agents to perform comprehensive security assessments.3-
- AlicenseNot gradedqualityBmaintenanceProduction-grade MCP server that exposes Kali Linux penetration testing tools to AI agents, enabling automated reconnaissance, web application testing, vulnerability assessment, and more.1MIT