Give text-only LLM agents eyes by describing images through a vision-language model via MCP or CLI.
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
huangzhixin0420
Source: Glama
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.
When Vitest UI server is listening, arbitrary file can be read and executed
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
AGENT_EYES_ALLOWED_DIRno working directory Root directory the file sandbox permits (relative paths still resolve against process.cwd()).AGENT_EYES_DISK_CACHEno (off) Set to 1 to persist the description cache to disk.AGENT_EYES_DISK_CACHE_DIRno os.tmpdir()/agent-eyes-mcp/cache Disk cache directory (created lazily).ANTHROPIC_API_KEYanthropic https://api.anthropic.com claude-haiku-4-5 (falls back to VISION_API_KEY). detail ignored.ANTHROPIC_BASE_URLno https://api.anthropic.com Anthropic Messages API base URL.ANTHROPIC_MODELno claude-haiku-4-5 Anthropic model name.GEMINI_API_KEYgemini https://generativelanguage.googleapis.com gemini-2.5-flash (falls back to VISION_API_KEY). detail ignored.GEMINI_BASE_URLno https://generativelanguage.googleapis.com Gemini generateContent base URL.GEMINI_MODELno gemini-2.5-flash Gemini model name.OLLAMA_BASE_URLno http://localhost:11434 Local Ollama base URL.OLLAMA_MODELno qwen2.5vl Ollama vision model name (must be pulled first).VISION_API_KEYexport =sk-... # required (default provider)VISION_BASE_URLexport =https://api.minimaxi.com/v1VISION_MODEL"": "qwen-vl-max"VISION_PROVIDERFour provider backends — OpenAI-compatible (default, e.g. DashScope / MiniMax), Anthropic, Google Gemini, and local Ollama, selected with .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
1/1 tools missing one or more hints — describe_image (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint). 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.
Production dependencies are patched
0 critical, 1 high severity in production deps — @modelcontextprotocol/sdk@1.0.0 (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.
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/huangzhixin0420-agent-eyes-mcp-1qokki)?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