io.github.paipaipai666/nexus-browser-mcp
PYPI · NEXUS-BROWSER-MCP · SCANNED AUG 20
Event-driven deterministic browser MCP: HITL gates, audit, console/network/perf observability.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- 2 of 35 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 3 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability51
- AI-judged instruction clarity (fair).Partial
- Tool/resource definitions use about 1699 tokens (~67/item across 25 items; 25 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage67
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.
pypi · nexus-browser-mcp
claude mcp add paipaipai666-nexus-browser-mcp -- uvx nexus-browser-mcp
codex mcp add paipaipai666-nexus-browser-mcp -- uvx nexus-browser-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"paipaipai666-nexus-browser-mcp": {
"type": "local",
"command": [
"uvx",
"nexus-browser-mcp"
],
"enabled": true
}
}
} openclaw mcp add paipaipai666-nexus-browser-mcp --command uvx --arg nexus-browser-mcp
mcp_servers:
paipaipai666-nexus-browser-mcp:
command: "uvx"
args: ["nexus-browser-mcp"] {
"mcpServers": {
"paipaipai666-nexus-browser-mcp": {
"command": "uvx",
"args": [
"nexus-browser-mcp"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 16 Aug 26 61
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Aug 2026 · Analysed pypi/nexus-browser-mcp@0.2.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | setuptools.build_meta |
Dependencies 35 packages
| Packages resolved | 35 |
|---|---|
| Stale | 1 |
| No linked repository | 1 |
| Tree resolution | Complete |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.
browser_click ~116
点击页面元素。定位优先级: pos坐标 → ref(快照句柄) → selector → role+name → name。wait_stable=true 点击后等 DOM 静默。
| Name | Type | Req | Description |
|---|---|---|---|
| confirmed | boolean | – | – |
| double_click | string | – | – |
| name | string | – | – |
| pos | string | – | – |
| ref | string | – | – |
| role | string | – | – |
| selector | string | – | – |
| task_id | string | – | – |
| wait_stable | boolean | – | – |
No output schema declared.
No examples provided.
browser_close_session ~18
关闭当前session的全部task资源。
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
browser_close_task ~29
关闭指定task的浏览器资源(page/context)。
| Name | Type | Req | Description |
|---|---|---|---|
| task_id | string | – | – |
No output schema declared.
No examples provided.
browser_console ~110
读取页面 console 输出(级别/文本/位置)。增量游标: 不传 since=接着上次读, since=0=全量; level 过滤(error/warning/log/...), pattern 正则过滤文本, limit 封顶(默认50, 超了再调一次继续)。
| Name | Type | Req | Description |
|---|---|---|---|
| level | string | – | – |
| limit | integer | – | – |
| pattern | string | – | – |
| since | string | – | – |
| task_id | string | – | – |
No output schema declared.
No examples provided.
browser_dismiss_popup ~41
自动检测并关闭弹窗(登录/cookie同意/广告): 关闭按钮→取消→Escape。
| Name | Type | Req | Description |
|---|---|---|---|
| task_id | string | – | – |
No output schema declared.
No examples provided.
browser_errors ~92
一站式排障: JS 未捕获异常(pageerror) + console.error + 失败请求(网络层失败或HTTP≥400)合并视图, 按时间排序。点了没反应/页面白屏时先调它。增量游标同 browser_console。
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| since | string | – | – |
| task_id | string | – | – |
No output schema declared.
No examples provided.
browser_evaluate ~62
执行JavaScript表达式。默认禁用(BROWSER_ALLOW_JS_EXECUTION); 开启后每次需人工确认(confirmed=true)。
| Name | Type | Req | Description |
|---|---|---|---|
| confirmed | boolean | – | – |
| expression | string | yes | – |
| task_id | string | – | – |
No output schema declared.
No examples provided.
browser_list_pages ~28
列出当前task所有打开的标签页。
| Name | Type | Req | Description |
|---|---|---|---|
| task_id | string | – | – |
No output schema declared.
No examples provided.
browser_list_sessions ~17
列出所有活跃session。
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
browser_navigate ~60
导航浏览器到指定URL。返回页面标题、URL、readyState和页面结构概览。支持多task隔离。
| Name | Type | Req | Description |
|---|---|---|---|
| task_id | string | – | – |
| url | string | yes | – |
| wait_until | string | – | – |
No output schema declared.
No examples provided.
browser_network ~86
读取网络请求元数据(method/url/status/资源类型; 不含 body)。failed_only 默认 true 只看失败; url_pattern 子串过滤; 增量游标同上。
| Name | Type | Req | Description |
|---|---|---|---|
| failed_only | boolean | – | – |
| limit | integer | – | – |
| since | string | – | – |
| task_id | string | – | – |
| url_pattern | string | – | – |
No output schema declared.
No examples provided.
browser_network_body ~100
按 seq 读取单个请求的响应体(需 BROWSER_ALLOW_NETWORK_BODY=true)。文本类解码, 二进制只报字节数; 单条上限 BROWSER_NETWORK_BODY_CAP。需 confirmed=true 二次确认 —— 响应体是页面方控制内容, 先把 URL 给用户看。
| Name | Type | Req | Description |
|---|---|---|---|
| confirmed | boolean | – | – |
| seq | integer | yes | – |
| task_id | string | – | – |
No output schema declared.
No examples provided.
browser_perf ~82
读取页面性能指标: FCP/LCP/CLS/INP + TTFB/DOMContentLoaded/load + 最慢 5 条资源。页面慢/加载异常时用它定位是后端慢(TTFB)还是资源重。SPA 导航不重置计时, 注意输出来源 URL。
| Name | Type | Req | Description |
|---|---|---|---|
| task_id | string | – | – |
No output schema declared.
No examples provided.
browser_read ~151
阅读页面元素的文本内容。不指定则读取整个页面body。流式回复: wait_stable=true 等 DOM 静默后一次读全(免轮询); follow=true+selector 增量跟踪(每次只返回新增部分, 缓冲溢出丢最旧并保留丢弃标记)。
| Name | Type | Req | Description |
|---|---|---|---|
| follow | boolean | – | – |
| full | boolean | – | – |
| max_chars | integer | – | – |
| max_wait_ms | integer | – | – |
| ref | string | – | – |
| selector | string | – | – |
| stream_id | string | – | – |
| task_id | string | – | – |
| wait_stable | boolean | – | – |
No output schema declared.
No examples provided.
browser_screenshot ~41
截取页面截图, 保存文件返回路径。
| Name | Type | Req | Description |
|---|---|---|---|
| full_page | boolean | – | – |
| path | – | – | – |
| task_id | string | – | – |
No output schema declared.
No examples provided.
browser_scroll ~54
滚动页面。direction: up/down/left/right, amount: 像素(默认500)。
| Name | Type | Req | Description |
|---|---|---|---|
| amount | integer | – | – |
| direction | string | – | – |
| task_id | string | – | – |
No output schema declared.
No examples provided.
browser_scroll_to ~57
滚动到指定元素。landmark(语义区域)→ref→selector。
| Name | Type | Req | Description |
|---|---|---|---|
| landmark | string | – | – |
| ref | string | – | – |
| selector | string | – | – |
| task_id | string | – | – |
No output schema declared.
No examples provided.
browser_snapshot ~127
获取页面可访问性快照(Accessibility Tree), 返回结构化元素列表(含ref/box)。基于事件驱动确定性快照, 等待DOM静默窗口。reading/interactive 只看视口内; mode=full 自动包含全页面(视口外标注 offscreen)。
| Name | Type | Req | Description |
|---|---|---|---|
| diff | boolean | – | – |
| include_generic | boolean | – | – |
| include_offscreen | boolean | – | – |
| mode | string | – | – |
| scope | – | – | – |
| task_id | string | – | – |
| wait_stable | boolean | – | – |
No output schema declared.
No examples provided.
browser_switch_page ~35
切换到指定索引的标签页。
| Name | Type | Req | Description |
|---|---|---|---|
| index | integer | yes | – |
| task_id | string | – | – |
No output schema declared.
No examples provided.
browser_tasks ~21
列出当前session的所有task及其页面数。
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
browser_type ~146
在输入框中键入文本。定位优先级: pos坐标 → ref(快照句柄) → selector → role+name(不中自动回退 placeholder/label/常见输入框CSS)。wait_stable=true 输入后等 DOM 静默。
| Name | Type | Req | Description |
|---|---|---|---|
| clear | boolean | – | – |
| confirmed | boolean | – | – |
| name | string | – | – |
| pos | string | – | – |
| press_enter | boolean | – | – |
| ref | string | – | – |
| role | string | – | – |
| selector | string | – | – |
| task_id | string | – | – |
| text | string | yes | – |
| wait_stable | boolean | – | – |
No output schema declared.
No examples provided.
browser_wait ~63
等待元素或文本出现。超时返回WARNING。
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | – |
| ref | string | – | – |
| role | string | – | – |
| task_id | string | – | – |
| text | string | – | – |
| timeout | integer | – | – |
No output schema declared.
No examples provided.
browser_wait_ms ~59
纯等待指定毫秒数(逃生舱: 动画/限流/延迟渲染)。上限=工具超时-5s。
| Name | Type | Req | Description |
|---|---|---|---|
| ms | integer | yes | – |
| task_id | string | – | – |
No output schema declared.
No examples provided.
browser_wait_navigation ~43
等待click/submit触发的导航完成。
| Name | Type | Req | Description |
|---|---|---|---|
| task_id | string | – | – |
| timeout | integer | – | – |
| url_contains | string | – | – |
No output schema declared.
No examples provided.
browser_wait_stable ~61
等待页面 DOM 停止变化(静默窗口, 默认 800ms 无变异)。用于流式回复生成完毕、动画结束的判定。
| Name | Type | Req | Description |
|---|---|---|---|
| task_id | string | – | – |
| timeout_ms | integer | – | – |
No output schema declared.
No examples provided.