C
Emerging
74/100
12 days ago

agent-eyes

Giving Agent Eyes to see and interact with internet. Agent Eye is an MCP server that wraps Playwright and exposes browser tools for local AI agents

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. 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

henry0hai

Source: github_code · also listed on 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
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.
// 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_EYE_FOCUSED_CONTENT_MULTIPLIER
configAGENT_EYE_FOCUSED_CONTENT_PAYLOAD_PREVIEW_CHARS
configAGENT_EYE_FOCUSED_CONTENT_PROMPT_CHARS
configAGENT_EYE_FOCUSED_CONTENT_PROMPT_CHUNK_CHARS
configAGENT_EYE_FOCUSED_CONTENT_PROMPT_MAX_CHUNKS
configAGENT_EYE_FOCUSED_CONTENT_SPILL_THRESHOLD_CHARS
configAGENT_EYE_FOCUSED_CONTENT_SPILL_TO_DISK
configAGENT_EYE_HEADLESS
configAGENT_EYE_MAX_CHARS
configAGENT_EYE_MODELdeep-seekllama2default (content-budget profile for browser_get_content, not Ollama model name)
configAGENT_EYE_NAV_TIMEOUT_MS
configAGENT_EYE_PROFILE
configAGENT_EYE_PROFILE_ROOT~/.agent-eye/profiles
configAGENT_EYE_SKILL_STALE_FAILURE_THRESHOLD2 (refresh skill after repeated selector failures)
configAGENT_EYE_SKILL_STALE_FOCUSED_CHARS400 (refresh skill if cached focused content is too small)
configAGENT_EYE_SKILL_STALE_SELECTOR_MATCHES1 (refresh skill if cached selectors barely match DOM)
configAI_LIVE_QUERY
configLLM_EVALUATE
configOLLAMA_BASE_URL
configOLLAMA_KEEP_ALIVEUse =10m (or higher) for smoother multi-step and chunked-answer runs
configOLLAMA_MODELgemma4:e4b-it-q4_K_M
configOLLAMA_NUM_CTX16384 (shared across all calls)
configRUN_EVAL_TESTStrue npx vitest run tests/eval/agent-eval.test.ts
// 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

13/13 tools missing one or more hints — ai_orchestrate_workflow (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ai_plan_goal (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); browser_analyze_page (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +10 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 inputs are validated

Only 0/13 tool handlers declare input schemas (0%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool test coverage

8/13 tools referenced in tests (62%)

Write tests that reference each tool by name so every tool has at least one test.

No eval / new Function

3 eval() or new Function() calls — dynamic code execution

Replace eval / Function with explicit parsing or safer alternatives.

Shell command execution

1 child_process call — runs shell commands

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

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 6 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 Score](https://m8ven.ai/badge/mcp/henry0hai-agent-eyes-3lwdxv)](https://m8ven.ai/mcp/henry0hai-agent-eyes-3lwdxv)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: ebad794c7a2a1fdf06499287f5f64f1323b99474
code hash: d2d6fbe1887141146b7e928c39be79946ded8cc57661d988e35cb79992f7c744
verified: 8/8/2026, 7:28:28 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