Multi-Agent AI Coding Assistant with parallel agent execution, enterprise security, and rich terminal UI. Built with TypeScript, Headaches @ SAAAM LLC
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
michaeldubu
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.
screenshot-desktop vulnerable to command Injection via `format` option
When Vitest UI server is listening, arbitrary file can be read and executed
glob CLI: Command injection via -c/--cmd executes matches with shell:true
ws affected by a DoS when handling a request with many HTTP headers
ws: Memory exhaustion DoS from tiny fragments and data chunks
ANTHROPIC_API_KEYGOOGLE_API_KEYNEXUS_ALLOW_COMPUTER_USEOPENAI_API_KEYGEMINI_MODELTool 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
10/10 tools missing one or more hints — read_file (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); write_file (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); edit_file (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +7 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
Only 1/10 tools referenced in tests (10%)
Write tests that reference each tool by name so every tool has at least one test.
Shell command execution
14 child_process/subprocess calls in production code — runs shell commands (saaam-intelligence-plugin/context-intelligence.ts:234, saaam-intelligence-plugin/context-intelligence.ts:244, saaam-intelligence-plugin/context-intelligence.ts:254)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Secrets not logged
2 secret values sent to console.log
Redact or omit secret values from log output.
Production dependencies are patched
1 critical, 3 high severity in production deps — screenshot-desktop@1.15.0 (critical), glob@10.3.10 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dev dependencies
1 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
Dependency freshness
3/25 production deps abandoned (no release in 2+ years): yoga-layout-prebuilt@2022-05-25 (4.2y), ink-big-text@2023-04-05 (3.4y), ink-text-input@2024-05-21 (2.2y)
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/michaeldubu-nexus-code-cli-emjurb)?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