Hunter (GeniusHu-tgty/Hunter) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 208 tools. The publisher has proved control of what we score (Verified Publisher). It is connected through the M8ven GitHub App, so the listing is re-checked on every push.

Back to MCP Trust IndexM8ven
C
Caution
74/100
5 days ago

Hunter

AI-driven penetration testing MCP server that equips Claude with 13 tools for automated reconnaissance, analysis, vulnerability validation, and exploitation.

→ GeniusHu-tgty/Hunter· listed on glama

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

⚡ Live Monitored

Monitored 5 days · every push re-verified

Who stands behind it

gmail.com (@GeniusHu-tgty) · Verified Publisher

Source: Glama

Install from

Glama

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
⚠️
Tool descriptions don’t match what handlers do
1 tool describes read intent but its handler mutates — hunter_healthcheck (line 4020: probe.write_text("ok", encoding="utf-8"))
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
✅
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 2 credentials: ACUNETIX_PASSWORD, HUNTER_REPLAY_SECRET
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
Are you the publisher? Confirm or correct these findings.
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configHUNTER_MEMORY_DB
configHUNTER_CASES_ROOT
configHUNTER_ALLOW_PRIVATE_JS_ANALYSIS
configHUNTER_CONTRACT_STRICT
configGOPROXY
configHUNTER_CDP_URL
configHUNTER_BROWSER_NAVIGATION_TIMEOUT_MS
configHUNTER_BROWSER_ALLOW_HEADLESS
configNO_PROXY
configno_proxy
configHUNTER_FP_ROOT
configBURP_MCP_URL
configBURP_PROXY_URL
configBURP_SESSION_GATE_WAIT
configOPEN_TGTYLAB_ROOT
configCODEX_HOME
configOPEN_TGTYLAB_WORKSPACE
configHUNTER_ROOT
configHUNTER_PROXY_FILE
configHUNTER_PROXIES
configHUNTER_DUMP_ROOT
configACUNETIX_CONFIG
configACUNETIX_EMAIL
configACUNETIX_PASSWORD_SHA256
🔐 secretACUNETIX_PASSWORD
configACUNETIX_BASE_URL
configHUNTER_DALFOX_BIN
configHUNTER_EDU_IP_DB
🔐 secretHUNTER_REPLAY_SECRET
configHUNTER_NUCLEI_BIN
configHUNTER_NUCLEI_TEMPLATES
configHUNTER_AUTH_PROFILES
// quality suggestions

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

208/208 tools missing one or more hints — hunter_scan (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); hunter_fast_scan (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); hunter_scan_plan (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +205 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.

Destructive tools are labelled

1 tool perform destructive updates without destructiveHint — hunter_healthcheck deletes at line 4021 (probe.unlink(missing_ok=True))

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

Descriptions match behaviour

1 tool describes read intent but its handler mutates — hunter_healthcheck (line 4020: probe.write_text("ok", encoding="utf-8"))

Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.

Tool description accuracy

hunter_healthcheck: description implies read-only but handler writes/deletes/executes

Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.

// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/geniushu-tgty/hunter?variant=verified)](https://m8ven.ai/mcp/geniushu-tgty/hunter)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 333d0c57fb3bbc152be06242fc93bf50c12f89ef
code hash: 1b9da87643926d1b94149d89f4c37428ede4215b3bb702d74ebf9fecef23600a
verified: 9/5/2026, 7:46:09 AM
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

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
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client