timesfm
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Read AI security guides and lab research, and request an LLM or AI agent security assessment.
教 AI 做这类工作的 Skill,可与本项一起使用
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. Hook an AI agent up to have it parse through data and find previously unseen correlations. The knowledge is available to…
scrape data from Google Maps. Extracts data such as the name, address, phone number, website URL, rating, reviews number, latitude and longitude, reviews,email and more for each place
此项在“连接 AI 的应用”标签中,该标签不使用星标,按以下顺序排列
| 1. 在 Claude 连接器目录中 | 否 | |
|---|---|---|
| 2. 团队实测过 | 否 | |
| 3. 适合泰国用户 | 否 | |
| 4. 不计星标的使用量 | 20/100 | 热度 0 · 新鲜度 12 · 仍在响应 8 |
| 5. 登记日期 | 2026-11-10 |
质量: 基础检查通过 4/5 项(仅展示,不用于排序)
选择你使用的 AI 应用,然后复制设置。
通过 4/5 项检查 · 你的提问会经过开发者的服务器(airedteamingservices.com) · ✓ 命令已检查 2026年11月13日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude · 约 2 分钟
不需要密钥,不用安装程序 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加
CustomizeConnectors
把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue
AI application security research and assessmentshttps://airedteamingservices.com/mcp在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add
+ConnectorsAI application security research and assessments
用 AI application security research and assessments 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 AI application security research and assessments,或回答中出现 AI application security research and assessments 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
能否连接 ChatGPT 取决于方案
完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页
Plugins+Add custom MCP server
输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin
AI application security research and assessmentshttps://airedteamingservices.com/mcp开启新聊天,输入前先从插件列表中选择 AI application security research and assessments
用 AI application security research and assessments 告诉我你能帮我做什么,然后做一件给我看✓ 如果 ChatGPT 说正在使用 AI application security research and assessments,或回答中出现 AI application security research and assessments 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Claude Code · 约 2 分钟
不需要密钥,不用安装程序
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
claude mcp add --transport http --scope user site https://airedteamingservices.com/mcp应能看到 AI application security research and assessments 在列表中并显示已连接
用 AI application security research and assessments 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 AI application security research and assessments,或回答中出现 AI application security research and assessments 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor · 约 2 分钟
不需要密钥,不用安装程序
用 AI application security research and assessments 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 AI application security research and assessments,或回答中出现 AI application security research and assessments 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code · 约 2 分钟
不需要密钥,不用安装程序
用 AI application security research and assessments 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 AI application security research and assessments,或回答中出现 AI application security research and assessments 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看
通过网页连接的应用使用的地址
https://airedteamingservices.com/mcpJSON 设置在下方“开发者专用”中
Claude Code
claude mcp add --transport http --scope user site https://airedteamingservices.com/mcpCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"site": {
"url": "https://airedteamingservices.com/mcp"
}
}
}VS Code (mcp.json)
{
"servers": {
"site": {
"type": "http",
"url": "https://airedteamingservices.com/mcp"
}
}
}这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
通过互联网连接,适用于
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
工具名称和描述与服务器在 2026年11月15日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
search_siteSearch the guides, service pages and research on airedteamingservices.com. Returns titles, URLs and one-line summaries.
get_pageReturn the Markdown text of a page on airedteamingservices.com, given its path (for example /guides/).
how_to_contactReturn the form URL and email address a person can use to contact Excession Labs. This tool does not send anything.
request_pentestSend a request for a penetration test or an AI application security assessment to Excession Labs on behalf of a person who asked for it. Needs an agent key (POST /agent/auth, then Authorization: Bearer ). Excession Labs replies to the person by email to agree scope; testing start
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月16日
发布者(airedteamingservices.com)不是仓库所有者(Excession-Labs);可能是其他人代为上架的
代码最后更新于4天前
使用 MIT
在 80 毫秒内响应(HTTP 200)
无需登录
已读取 4 个工具描述,未发现针对 AI 的隐藏指令
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/airedteamingservices-site)提问、分享技巧或报告无法使用。按“有帮助”数量排序。
还没有评价
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 5 项适用的基础检查中通过了 4 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于4天前,最新版本(1.1.0)于6天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。
同一分类中有:OpenSEO, Exa, Mockserver, Microsoft Learn MCP, Docs
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Keyword research, site audits, rank tracking and AI visibility for your AI agent.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Mock, record/replay, verify and chaos-test any HTTP, REST, gRPC or LLM dependency over MCP.
Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.
| 本项 AI application security research and assessments | OpenSEO | Exa | Mockserver | Microsoft Learn MCP | Docs | |
|---|---|---|---|---|---|---|
| 运行位置 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 需要安装在电脑上 | 在云端运行,无需安装 | 在云端运行,无需安装 |
| 需要密钥 | 否 | 否 | 否 | 否 | 否 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 是 | 是 | 否 | 是 | 否 |
| 基础检查 | 4/5 | 5/5 | 2/4 | 3/3 | 4/4 | 4/4 |
| 许可证 | MIT | MIT | MIT | Apache-2.0 | CC-BY-4.0 | NOASSERTION |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Four hosted MCP services run by Excession Labs, a security lab. They use Streamable HTTP and are listed in the official MCP Registry. This repository contains documentation, public tool schemas and discovery metadata. Connect to a hosted URL to use a service.
The MIT licence covers this documentation repository. The hosted server implementations are maintained separately; this repository does not contain their source code or a self-hostable package.
| Server (registry name) | URL | Tools |
|---|---|---|
ai.excessionlabs/site | https://excessionlabs.ai/mcp | Six CVE tools, search_site, get_page, how_to_contact, request_security_test |
com.penetrationtestservices/site | https://penetrationtestservices.com/mcp | check_security_headers, request_pentest, search_site, get_page, how_to_contact |
com.pentestcompare/site | https://pentestcompare.com/mcp | list_providers, get_provider, search_site, get_page, how_to_contact |
com.airedteamingservices/site | https://airedteamingservices.com/mcp | request_pentest (AI application assessments), search_site, get_page, how_to_contact |
For CVE queries, use the public, read-only endpoint at https://excessionlabs.ai/mcp/cve. It exposes only cve_search, cve_get, cve_history, cve_status, cve_sources and cve_changes. It requires no account or API key. The main /mcp endpoint includes those six tools and the four site tools; its request_security_test action writes a request and needs an agent key.
CVE connection guide and examples · Public CVE documentation · Privacy policy
Full tool definitions: servers/ .tools.json. The CVE-only definitions are in excessionlabs-cve.tools.json. Server cards: servers/ .server-card.json. Registry entries: servers/ .server.json. The CVE endpoint is another view of the Excession service; it does not have a separate registry namespace in this repository.
All six CVE tools and Excession's site information tools are public. Excession applies request limits and can return HTTP 429 with Retry-After; reduce request frequency and follow that header. CVE result lists are paginated. See the CVE guide for result bounds and source coverage.
For penetrationtestservices.com, pentestcompare.com and airedteamingservices.com, reading needs no credential: 120 requests a minute per IP. An optional anonymous agent key from POST https:// /agent/auth raises that to 600 a minute (details in https:// /auth.md).
request_pentest needs the key. It sends a test request to Excession Labs for a person who asked for one. person_consent and authorized must be true. Excession Labs replies to the person by email, and testing starts only after a written scope and written authorization. Limits: 5 requests a day per key and 3 a day per email address. Never send passwords, keys or customer data.
On excessionlabs.ai, the equivalent action is request_security_test, with an agent key from POST https://excessionlabs.ai/agent/auth. It has the same consent and authorization requirements and submission limits. It is available only on the main /mcp endpoint.
All other tools are read-only. Public CVE access is free. Security assessment services are separate; using the connector does not order a test.
Claude Code:
claude mcp add --transport http excession-cve https://excessionlabs.ai/mcp/cve
claude mcp add --transport http pentestcompare https://pentestcompare.com/mcp claude mcp add --transport http penetrationtestservices https://penetrationtestservices.com/mcp claude mcp add --transport http airedteamingservices https://airedteamingservices.com/mcp
Gemini CLI users can install the CVE-only extension from this repository:
gemini extensions install https://github.com/Excession-Labs/mcp-servers
The extension connects only to the six read-only CVE tools and needs no account or API key.
Excession Labs also publishes security review skills and related site connectors at https://github.com/Excession-Labs/claude-plugins.
Any MCP client that supports Streamable HTTP can use the URLs above.
curl -sS https://excessionlabs.ai/mcp/cve \
-H 'Content-Type: application/json' \ -H 'Accept: application/json, text/event-stream' \ -H 'MCP-Protocol-Version: 2025-11-25' \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"cve_get","arguments":{"cve_id":"CVE-2024-3094","affected_limit":10}}}'
MCP clients perform initialization before tool calls. A complete initialization example is in the CVE guide.
Provider facts come from each provider's own public pages, with the date checked: https://github.com/Excession-Labs/pentest-provider-dataset. Excession Labs publishes PentestCompare and also sells security testing; its own row is marked publisher_owned.
CVE records retain their source references. The import baseline has more than 424,000 CVE records and about 1.57 million software/version assertions. These are baseline counts, not a claim of complete enrichment or distinct software versions. Read cve_status for the current counts, per-source checkpoints and backlog. Software/version searches match source assertions; they do not evaluate whether an installed version falls within a vulnerability range. Hosted revision history begins at the cutover date returned by the server. Initial hosted observations establish a baseline and do not necessarily mean the upstream advisory changed.
The hosted collector runs every ten minutes in bounded batches. Source schedules differ, and catch-up can take several runs. EPSS refresh rotates through recent and KEV-listed CVEs; other scores retain their snapshot dates. Retained revisions normalize source evidence and preserve shared affected_groups referenced by version claims' group_id values.
See the CVE guide for source attribution and coverage limits.
Public support: support@excessionlabs.ai. The Excession connector's privacy policy and terms apply to its hosted service. Each other service publishes its own policy at /privacy/ on its domain.
Documentation licence: MIT. Source data has its own terms and attribution.