C
Caution
74/100
2 days ago

agent-eyes-mcp

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

Code Verified⚡ Live Monitored: not connected

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

Is this your MCP?

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.

// key findings
🚨
Known vulnerabilities in dependencies: 1 critical, 1 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
🔐
You'll be asked for 3 credentials: ANTHROPIC_API_KEY, GEMINI_API_KEY, VISION_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// known CVEs in dependencies1 critical1 high

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

criticalvitest@2.1.9GHSA-5xrq-8626-4rwp

When Vitest UI server is listening, arbitrary file can be read and executed

high@modelcontextprotocol/sdk@1.0.0GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// 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.
configAGENT_EYES_ALLOWED_DIRno working directory Root directory the file sandbox permits (relative paths still resolve against process.cwd()).
configAGENT_EYES_DISK_CACHEno (off) Set to 1 to persist the description cache to disk.
configAGENT_EYES_DISK_CACHE_DIRno os.tmpdir()/agent-eyes-mcp/cache Disk cache directory (created lazily).
🔐 secretANTHROPIC_API_KEYanthropic https://api.anthropic.com claude-haiku-4-5 (falls back to VISION_API_KEY). detail ignored.
configANTHROPIC_BASE_URLno https://api.anthropic.com Anthropic Messages API base URL.
configANTHROPIC_MODELno claude-haiku-4-5 Anthropic model name.
🔐 secretGEMINI_API_KEYgemini https://generativelanguage.googleapis.com gemini-2.5-flash (falls back to VISION_API_KEY). detail ignored.
configGEMINI_BASE_URLno https://generativelanguage.googleapis.com Gemini generateContent base URL.
configGEMINI_MODELno gemini-2.5-flash Gemini model name.
configOLLAMA_BASE_URLno http://localhost:11434 Local Ollama base URL.
configOLLAMA_MODELno qwen2.5vl Ollama vision model name (must be pulled first).
🔐 secretVISION_API_KEYexport =sk-... # required (default provider)
configVISION_BASE_URLexport =https://api.minimaxi.com/v1
configVISION_MODEL"": "qwen-vl-max"
configVISION_PROVIDERFour provider backends — OpenAI-compatible (default, e.g. DashScope / MiniMax), Anthropic, Google Gemini, and local Ollama, selected with .
// 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

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.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/huangzhixin0420-agent-eyes-mcp-1qokki?variant=verified)](https://m8ven.ai/mcp/huangzhixin0420-agent-eyes-mcp-1qokki)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 7b351785f54ae157a75195b5db2d8db1f34c1760
code hash: b42a139a73c47d9266a2851f10c595adeb9a0463750976fc790f4931be4f707b
verified: 8/17/2026, 9:24:19 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