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
GeniusHu-tgty
Source: github_code
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
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
sm-crypto: Predictable SM2 key generation in Node.js: default RNG uses Math.random + wall clock
axios Vulnerable to Full Man-in-the-Middle via Prototype Pollution Gadget in `config.proxy`
Allocation of Resources Without Limits or Throttling in Axios
Axios Node HTTP adapter can use an inherited proxy after interceptor config cloning
Axios: Regular Expression Denial of Service (ReDoS) via Cookie Name Injection
ANTHROPIC_API_KEY"your_key"ANTHROPIC_BASE_URLANTHROPIC_MODEL"claude-3-5-sonnet-20241022"BROWSER_CHANNELBROWSER_EXECUTABLE_PATHBROWSER_HEADLESSBROWSER_ISOLATEDDEFAULT_LLM_PROVIDER"anthropic"GEMINI_API_KEYgemini 支持两种模式：有 时走 API；没有时会尝试走 GEMINI_CLI_PATHGEMINI_CLI_PATHgemini-cliGEMINI_MODELgemini-2.0-flash-expJSREVERSER_ARTIFACTS_DIRLOG_LEVELOPENAI_API_KEYOPENAI_BASE_URLOPENAI_MODELREMOTE_DEBUGGING_PORTREMOTE_DEBUGGING_URLUSE_STEALTH_SCRIPTSXDG_STATE_HOMEDependencies
48 dependencies, 3 flagged: puppeteer-core, puppeteer-extra, puppeteer-extra-plugin-stealth
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
110/110 tools missing one or more hints — recommend_next_step (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); explain_reverse_stage (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); run_reverse_agent (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +107 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.
Tool test coverage
67/110 tools referenced in tests (61%)
Write tests that reference each tool by name so every tool has at least one test.
No eval / new Function
8 eval() or new Function() calls — dynamic code execution
Replace eval / Function with explicit parsing or safer alternatives.
Shell command execution
3 child_process/subprocess calls in production code — runs shell commands (src/services/GeminiProvider.ts:292, src/services/GeminiProvider.ts:372, src/modules/browser/BrowserModeManager.ts:97)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Production dependencies are patched
1 critical, 7 high severity in production deps — sm-crypto@0.4.0 (critical), axios@1.15.2 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dependency freshness
3/20 production deps abandoned (no release in 2+ years): puppeteer-extra@2023-03-01 (3.5y), puppeteer-extra-plugin-stealth@2023-04-11 (3.4y), xbogus@2023-12-23 (2.7y)
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/geniushu-tgty-open-tgtylab-h3gb5n)?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