LR-Agent
基于 Electron + React + FastAPI + LangChain 的多模态 AI 智能标注平台。支持矩形框、旋转框、多边形、关键点、图像/文本分类、Caption、指令遵循、思维链与实体识别等标注场景，以及多轮对话、长短期记忆与 Agent Skills。智能体基于 Tool-Use-Loop 自主规划，按需调用工作区检索、自动标注、会话记忆、技能加载及 MCP 工具完成任务。
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
MarisaMagic
Source: github_repo_search
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
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Electron: Use-after-free in offscreen child window paint callback
Electron: Use-after-free in WebContents fullscreen, pointer-lock, and keyboard-lock permission callbacks
Electron: Sandboxed iframe can bypass the allow-popups restriction via the OpenURL navigation path
Electron: Renderer command-line switch injection via undocumented commandLineSwitches webPreference
Electron: Context isolation bypass via Function.prototype.bind hijack
API_BASE_URLCONDA_PREFIXLR_AGENT_INFERENCE_CONDA_ENVLR_AGENT_INFERENCE_PYTHONLR_AGENT_LOCAL_CONDA_ENVLR_AGENT_LOCAL_PYTHONLR_AGENT_LOCAL_PORTPORTTool 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
9/9 tools missing one or more hints — memory_read (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); read_agent_skill (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_agent_skill_files (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +6 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 2/9 tool handlers declare input schemas (22%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool test coverage
7/9 tools referenced in tests (78%)
Write tests that reference each tool by name so every tool has at least one test.
No arbitrary install scripts
Has postinstall/preinstall script — runs arbitrary code on npm install
Remove postinstall/preinstall hooks unless they’re essential.
Production dependencies are patched
8 medium severity in production deps
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dev dependencies
7 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
Dependency freshness
3/32 production deps abandoned (no release in 2+ years): seti-icons@2022-05-17 (4.3y), remark-math@2023-11-20 (2.8y), rehype-katex@2024-08-19 (2.1y)
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/marisamagic/lr-agent)?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