Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, email [email protected] and we’ll put it right.

HackTricks MCP Server

NPM · HACKTRICKS-MCP-SERVER · SCANNED AUG 3

Search and query HackTricks pentesting documentation with quick lookup and section extraction

+22 this week 61 Trust /100
Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →

Supply Chain Security80
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.Partial
  • Runs a script at install time (postinstall) that we could not recognise. It may be perfectly ordinary, but we do not read the published tarball, so we cannot say what it does. View diagnostics → Partial
  • Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency19
Schema Quality & AI Usability73
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 943 tokens (~134/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
  • Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · hacktricks-mcp-server

# add to Claude Code
claude mcp add xplo8e-hacktricks-mcp-server -- npx -y hacktricks-mcp-server
# add to Codex CLI
codex mcp add xplo8e-hacktricks-mcp-server -- npx -y hacktricks-mcp-server
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "xplo8e-hacktricks-mcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "hacktricks-mcp-server"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add xplo8e-hacktricks-mcp-server --command npx --arg -y --arg hacktricks-mcp-server
# ~/.hermes/config.yaml
mcp_servers:
  xplo8e-hacktricks-mcp-server:
    command: "npx"
    args: ["-y", "hacktricks-mcp-server"]
// mcp.json
{
  "mcpServers": {
    "xplo8e-hacktricks-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "hacktricks-mcp-server"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 3 Aug 26 +4
    • Stability: unverified → 0.27 functional
  • 2 Aug 26 +42
    • Provenance: unverified → fail security
    • Install scripts: unverified → partial security
    • Known CVEs: unverified → partial security
    • Malware scan: unverified → pass security
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • The scripts that run when this package is installed changed: postinstall security
    • Tool coverage: 100 → unverified functional
    • Schema quality: unverified → excellent functional
    • License: unverified → pass functional
    • Maintenance: unverified → pass functional
    • MCP protocol: unverified → pass functional
    • Dependency health: unverified → partial functional
    • Licence: MIT functional
  • 1 Aug 26 −6
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 31 Jul 26 +3
    • Malware scan: pass → unverified security
    • Tool coverage: unverified → 100 functional
  • 28 Jul 26 −21
    • Tool coverage: 100 → unverified functional
    • First check of Schema quality: unverified functional
  • 27 Jul 26 39

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 3 Aug 2026 · Analysed npm/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Install scripts 1 script
Hook Tier Command
postinstall unreviewed node scripts/postinstall.js
Dependencies 94 packages

94 packages in the resolved dependency tree · 94 deprecated · 29 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 7 exposed · ~943 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens
get_hacktricks_cheatsheet ~84

Extract ALL CODE BLOCKS from a page (commands, payloads, scripts, one-liners). Skips explanatory text. Perfect for: 'give me the exploit command', 'show me the payload', 'what's the syntax'. Returns code with language tags (bash, python, etc.).

NameTypeReqDescription
pathstringyesPath from search results

No output schema declared.

No examples provided.

get_hacktricks_outline ~91

Get TABLE OF CONTENTS (all section headers) of a page. Returns ~20-50 lines showing page structure. Use this FIRST after search to: (1) verify page is relevant, (2) find exact section names for get_hacktricks_section. Cost: ~100 tokens vs 3000+ for full page.

NameTypeReqDescription
pathstringyesPath from search results

No output schema declared.

No examples provided.

get_hacktricks_page ~101

Get FULL page content. ⚠️ EXPENSIVE: Pages average 3000-15000 tokens. PREFER: get_hacktricks_section for specific topics, get_hacktricks_cheatsheet for just commands. Only use this when you need the complete page or multiple sections.

NameTypeReqDescription
pathstringyesPath from search results (e.g., 'src/linux-hardening/privilege-escalation/README.md')

No output schema declared.

No examples provided.

get_hacktricks_section ~147

Extract ONE SECTION from a page. MOST EFFICIENT way to read content. Typical sections: 'Exploitation', 'Enumeration', 'Prevention', 'Example', 'Payload', 'PoC', 'Bypass'. Use get_hacktricks_outline first to see exact section names. Returns ~200-500 tokens vs 3000+ for full page.

NameTypeReqDescription
pathstringyesPath from search results
sectionstringyesSection name (partial match, case-insensitive). From outline or common: 'exploitation', 'enumeration', 'bypass', 'payload', 'example', 'poc', 'prevention', 'detection'

No output schema declared.

No examples provided.

hacktricks_quick_lookup ~185

⚡ ONE-SHOT exploitation lookup. Searches, finds best page, and returns exploitation sections + code blocks. Use for: 'how do I exploit X', 'give me X payload', 'X attack technique'. Handles aliases (sqli→SQL injection, xss→Cross-site scripting, rce, lfi, ssrf, etc.). Returns: page title, exploitation sections, and top 5 code blocks.

NameTypeReqDescription
categorystringOptional category filter. Speeds up search. Common: 'pentesting-web', 'linux-hardening', 'windows-hardening', 'network-services-pentesting'
topicstringyesAttack/technique to look up. Examples: 'SUID', 'sqli', 'xss', 'ssrf', 'jwt', 'docker escape', 'kerberoasting'. Aliases auto-expand.

No output schema declared.

No examples provided.

list_hacktricks_categories ~104

Browse HackTricks structure. Without params: list all categories. With category: show all pages in that category. Use when: (1) unsure which category to search, (2) want to explore what's available, (3) need exact file paths.

NameTypeReqDescription
categorystringCategory to explore. Popular: 'pentesting-web', 'linux-hardening', 'windows-hardening', 'network-services-pentesting', 'mobile-pentesting'

No output schema declared.

No examples provided.

search_hacktricks ~231

Search HackTricks for pentesting techniques, exploits, and security info. Returns results GROUPED BY FILE with: page title, match count, relevant sections, and top matches. WORKFLOW: search → get_hacktricks_outline (see structure) → get_hacktricks_section (read specific part). ALWAYS use category filter when possible - saves time and tokens.

NameTypeReqDescription
categorystringSTRONGLY RECOMMENDED. Common categories: 'pentesting-web' (XSS,SQLi,SSRF), 'linux-hardening' (privesc,capabilities), 'network-services-pentesting' (SMB,FTP,SSH), 'windows-hardening', 'mobile-pentesti…
limitnumberMax files to return (default: 20). Lower = faster. Set to 5 for quick lookups.
querystringyesSearch term. Be specific (e.g., 'SUID privilege escalation' not just 'privilege'). Supports regex.

No output schema declared.

No examples provided.