hacktricks-mcp-server
MCP server for searching HackTricks documentation
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
Xplo8E
Source: Glama · also listed on npm
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
search_hacktricksSearch 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 fi…
get_hacktricks_pageGet 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.
get_hacktricks_outlineGet 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.
get_hacktricks_sectionExtract 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.
get_hacktricks_cheatsheetExtract 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.).
list_hacktricks_categoriesBrowse 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.
hacktricks_quick_lookup⚡ 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, exploitatio…
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
7/7 tools missing one or more hints — search_hacktricks (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_hacktricks_page (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_hacktricks_outline (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +4 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tests exist
No test files found
Add tests that exercise each declared tool.
No arbitrary install scripts
Has postinstall/preinstall script — runs arbitrary code on npm install
Remove postinstall/preinstall hooks unless they’re essential.
Production dependencies are patched
0 critical, 2 high severity in production deps — @modelcontextprotocol/sdk@1.25.1 (high), @modelcontextprotocol/sdk@1.25.1 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/xplo8e/hacktricks-mcp-server)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check