原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

endoflife.ai — Software Lifecycle Intelligence

✓ Brand-named GitHub · github.com/endoflife-ai

作者:endoflife-ai版本 1.4.1i★ 0i在云端运行官方网站 ↗
注册名称io.github.endoflife-ai/endoflife-mcp

安装方法

What it does

EOL dates, risk scores, CISA KEV exposure, SBOM audits and edge-device EOS for 700+ products.

  • Connects 在云端运行
  • Account or key Works without a key · add X-API-Key if you have one (often raises limits)
  • Category 其他

为什么排在这里

列表按使用分(满分 100)排序,由以下部分组成

热度0/80GitHub 星标或每周下载量:较大的计 60,较小的计 20
新鲜度12/1230 天内有发布或代码更新得满分
仍在响应8/8上次检查时云端端点有响应
使用分20/100

质量: 基础检查通过 5/5 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)

安装

选择你使用的 AI 应用,然后复制设置。

用一句话让 AI 帮你安装

请帮我安装 endoflife.ai — Software Lifecycle Intelligence。按照 https://mcp.popnx.com/i/endoflife-ai-endoflife-mcp.md 操作,先把命令给我看,等我同意后再运行。

粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文

通过 5/5 项检查 · 你的提问会经过开发者的服务器(mcp.endoflife.ai) · ✓ 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

  1. 打开 Claude 的 Connectors 页面

    CustomizeConnectors

    CustomizeConnectors1Add2https://…3Add4
  2. 点击“Add” → “Custom” → “Web”,填写这 2 项

    把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue

    Name · 名称endoflife.ai — Software Lifecycle Intelligence
    Remote MCP server URL · 地址https://mcp.endoflife.ai

    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

  3. 在聊天中开启

    +Connectorsendoflife.ai — Software Lifecycle Intelligence

  4. 试一试

    用 endoflife.ai — Software Lifecycle Intelligence 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 endoflife.ai — Software Lifecycle Intelligence,或回答中出现 endoflife.ai — Software Lifecycle Intelligence 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

  1. 在网页版 ChatGPT 打开添加 MCP 的页面

    Plugins+Add custom MCP server

    ChatGPTPlugins1+2https://…3Create4
  2. 填写名称和地址

    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

    Name · 名称endoflife.ai — Software Lifecycle Intelligence
    Connection · 地址https://mcp.endoflife.ai
  3. 在聊天中选择 endoflife.ai — Software Lifecycle Intelligence

    开启新聊天,输入前先从插件列表中选择 endoflife.ai — Software Lifecycle Intelligence

  4. 试一试

    用 endoflife.ai — Software Lifecycle Intelligence 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 endoflife.ai — Software Lifecycle Intelligence,或回答中出现 endoflife.ai — Software Lifecycle Intelligence 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

  1. 打开终端

    Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell

  2. 粘贴这条命令并按 Enter

    claude mcp add --transport http --scope user endoflife https://mcp.endoflife.ai
  3. 在 Claude Code 中输入 /mcp

    应能看到 endoflife.ai — Software Lifecycle Intelligence 在列表中并显示已连接

  4. 试一试

    用 endoflife.ai — Software Lifecycle Intelligence 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 endoflife.ai — Software Lifecycle Intelligence,或回答中出现 endoflife.ai — Software Lifecycle Intelligence 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

  1. 点击这个按钮打开 Cursor

    在 Cursor 中打开

    Cursor 会请你确认安装,点击 Install

  2. 在 Cursor 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 endoflife.ai — Software Lifecycle Intelligence 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 endoflife.ai — Software Lifecycle Intelligence,或回答中出现 endoflife.ai — Software Lifecycle Intelligence 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

  1. 点击这个按钮打开 VS Code

    在 VS Code 中打开

    VS Code 会请你确认安装,点击 Install

  2. 在 VS Code 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 endoflife.ai — Software Lifecycle Intelligence 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 endoflife.ai — Software Lifecycle Intelligence,或回答中出现 endoflife.ai — Software Lifecycle Intelligence 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

查看所有支持 MCP 的应用 →

通过网页连接的应用使用的地址

地址https://mcp.endoflife.ai

JSON 设置在下方“开发者专用”中

卡住了?问问正在用 endoflife.ai — Software Lifecycle Intelligence 的人💬 讨论 →
开发者专用:终端命令和 JSON 设置

通过网页连接

Claude Code

claude mcp add --transport http --scope user endoflife https://mcp.endoflife.ai

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "endoflife": {
      "url": "https://mcp.endoflife.ai"
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "endoflife": {
      "type": "http",
      "url": "https://mcp.endoflife.ai"
    }
  }
}

需要你填写的值

  • X-API-Key 机密 HTTP header
    可选的 endoflife.ai API 密钥(免费版、Starter 或 Pro),用于提高调用限额。不设置也可使用。
    查看英文原文Optional endoflife.ai API key (free, Starter or Pro) for higher limits. Works without one.

说明为自动翻译,变量名保持原样;不确定时请查看原文。

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。

一览

每周下载量i
不在 npm/PyPI 上
连接方式
在云端运行
传输方式
streamable-http
最新版本i
1.4.1
分类i
其他
发布到注册中心i
2026年11月3日
代码最后更新i
2026年11月16日
最近检查
2026年11月17日
作者
endoflife-ai
注册状态
活跃

哪些应用可以使用它

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

全部应用及其优缺点 →

它能做什么

工具名称和描述与服务器在 2026年11月17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。

  • check_eol

    Check whether a specific version of a software product is end-of-life (EOL). Returns lifecycle status, the EOL date, days remaining or days past EOL, the latest release, and eol_date_source (where the date comes from: vendor-override, vendor-fetched, vendor-verified, custom, upst

  • get_risk_score

    Get the proprietary EOL Risk Score (0-100) for a product version, with the four-factor breakdown (EOL recency, attack surface, CISA KEV exposure, extended support). Omit "version" to score the product's highest-risk (most recently end-of-lifed) release. Use this to quantify how d

  • scan_stack

    Audit a whole stack at once. Provide a list of products (optionally with versions) — e.g. parsed from a package.json or Dockerfile — and get an EOL Risk Score for each, so you can see what is unsupported and dangerous in one call. For CycloneDX or SPDX documents use check_sbom in

  • list_products

    List or search the 700+ products endoflife.ai tracks. Pass an optional "query" substring to find the canonical slug for a product before calling the other tools (e.g. "postgres" → "postgresql"). Returns matching product slugs.

  • get_product_lifecycle

    Get the full version history for one product: every tracked version/cycle with its release date, EOL date, support status, and EOL Risk Score. Use for "give me the whole EOL schedule for X".

  • get_kev_exposure

    The exploited-vulnerability record for a product: every CVE CISA lists against it in the Known Exploited Vulnerabilities catalog, with the date added, the federal due date and CISA's required-action text verbatim (the "discontinue use" entries are the ones that matter for end-of-

  • get_upcoming_eol

    What reaches end-of-life soon. Returns every tracked version whose EOL date falls within the next N days (default 90), optionally limited to a list of products, sorted by date. Also lists versions that went EOL within the last "recent_past_days" days when set. Use for "what in ou

  • get_edge_device_status

    Query the EOS Edge Device Intelligence feed — firewalls, VPN gateways and appliances, ADCs, router and switch operating systems — with end-of-support status in the vocabulary of CISA BOD 26-02 (eos, within-12-months, scheduled, no-date-announced). Filter by platform or vendor nam

  • get_upgrade_path

    Where to move a product version: the current version's support status and score, the supported releases with the longest remaining support, endoflife.ai's recommended target, and the vendor's stated successor where one is published (edge appliances). Use after check_eol says a ve

  • check_sbom

    Audit a CycloneDX or SPDX JSON software bill of materials. Components are mapped to tracked products and scored for EOL risk; unmatched components are listed honestly rather than guessed. Pass the SBOM as a JSON string or object. Versions resolve to their release family (python 3

基础检查i

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19日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 endoflife-ai 验证,该账户拥有此仓库

  • ✓ 通过

    仍在维护

    代码最后更新于3天前

  • ✓ 通过

    有许可证

    使用 MIT

  • ✓ 通过

    端点有响应

    在 47 毫秒内响应(HTTP 200)

  • – 不适用

    使用 OAuth 登录

    无需登录

  • ✓ 通过

    工具描述中没有隐藏指令

    已读取 10 个工具描述,未发现针对 AI 的隐藏指令

我们检查什么 → · JSON

作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/endoflife-ai-endoflife-mcp.svg)](https://mcp.popnx.com/en/servers/endoflife-ai-endoflife-mcp)

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

用户评价

还没有评价

登录后写评价

与“其他”中的其他服务器比较i

  • 星标数多于此分类中其他 20749 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 20749 个服务器的 74% 更新
  • 基础检查结果等于或优于此分类中其他 20749 个服务器的 99%

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。

常见问题

endoflife.ai — Software Lifecycle Intelligence 安全吗?

它在 5 项适用的基础检查中通过了 5 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。

它需要哪些密钥或代码?

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。

它在我的电脑上运行还是在云端?

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。

它还在维护吗?

GitHub 仓库最后更新于3天前,最新版本(1.4.1)于16天前进入注册中心。

哪些应用可以使用它?

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)。

有什么可以替代它?

同一分类中有:World Monitor, openstatus, Oh My Posh Validator, Strata, Jitsu

功能相近的其他选择

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

World Monitor

Real-time global intelligence on conflict, markets, energy, trade, shipping and cyber. 100 tools.

作者:koala73广泛使用★ 9.1万3天前更新

在云端运行✓ 服务方 · worldmonitor.app

openstatus

Manage monitors, status pages, incidents and maintenances in your openstatus workspace.

作者:openstatusHQ广泛使用★ 92742个月前更新

在云端运行✓ 服务方 · openstatus.dev

Strata

MCP server for progressive tool usage at any scale (see https://klavis.ai)

作者:Klavis-AI正在增长★ 582414个月前更新

在云端运行仓库已归档✓ klavis.ai

Jitsu

Manage Jitsu data pipelines: destinations, streams, connections, functions, live events.

作者:jitsucom广泛使用★ 51364个月前更新

在云端运行✓ 服务方 · jitsu.com
与相似项目对比
本项
endoflife.ai — Software Lifecycle Intelligence
World MonitoropenstatusOh My Posh ValidatorStrataJitsu
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
需要密钥否否否否否否
可在 Claude 中按 + 添加否否否否否否
基础检查5/54/44/44/41/44/4
许可证MITAGPL-3.0AGPL-3.0MITApache-2.0MIT
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

作者的 README

打开 README

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。

endoflife.ai — MCP Server

Exposes endoflife.ai's lifecycle intelligence to AI agents over the Model Context Protocol (MCP, Streamable HTTP transport). A dependency-free Cloudflare Worker that wraps the public api.endoflife.ai/v1 endpoints and the site's published feeds — no data duplicated, every answer carries a source URL.

Current version: 1.4.4 (SERVER_INFO.version in src/index.js, server.json, package.json, the Dockerfile ARG VERSION, and the site's endoflife/.well-known/mcp/server-card.json — keep them in step; the registry and Glama read server.json).

1.4.4: check_sbom declares its sbom input as object or string (the directory portal flags an input with no type).

1.4.3: scan_stack and check_sbom descriptions state the keyless per-call limit without naming plans (Claude Connectors Directory review: tool descriptions must not promote products); the limit note in answers is unchanged.

1.4.2: tools accept the argument shapes clients actually send (name, slug or cycle for product and version, "python 3.12" as one string, arguments as a JSON string, scan_stack items as strings or a comma list), and a missing argument gets an error that says what to send, with an example.

1.4.1: description and tool text carry the current build-computed counts (700+ products, 15,000+ versions) for the registry and npm listings; no behaviour change.

1.4.0: check_sbom is a thin proxy to the API's POST /v1/sbom (one resolver for every surface; versions keep their release family, e.g. python 3.12, ubuntu 20.04). Above the tier cap it returns the scored subset plus limit_note and not_scored_count; scan_stack scores the first N the tier allows and lists the rest in not_checked. Until 1.4.0 check_sbom cut every version to its major number and a keyless SBOM with more than 5 matched components returned nothing.

Tools (all read-only)

ToolWhat it doesBacked by
check_eolIs product X version Y end-of-life?GET /v1/status/:slug/:version
get_risk_scoreEOL Risk Score (0–100) + factor breakdownGET /v1/score/:slug[/:version]
scan_stackScore a whole stack at oncePOST /v1/batch
list_productsSearch the 700+ tracked products → resolve slugsGET /v1/products
get_product_lifecycleFull version history + dates for one productGET /v1/product/:slug
get_kev_exposureEvery CISA KEV entry attributed to a product (date added, due date, required action verbatim) + Exploited & Unpatchable entriesendoflife.ai/kev-products.json, exploited-and-unpatchable.json
get_upcoming_eolEverything reaching EOL in the next N days (catalog-wide or a product list)endoflife.ai/scanner-db.json
get_edge_device_statusEOS Edge Device feed with BOD 26-02 statuses, filter by platform / status / modelendoflife.ai/eos-edge-devices.json
get_upgrade_pathSupported targets, the site's recommendation, vendor-stated successorGET /v1/product/:slug, checker-db.json, edge feed
check_sbomCycloneDX / SPDX JSON → components resolved by package URL (exact, purl-map.json) or by name when no purl → scored up to the tier cap, the rest counted in a note; unmatched listed with a reason, never guessedPOST /v1/sbom

Every tool advertises annotations (readOnlyHint, idempotentHint) and a permissive outputSchema; results are returned both as JSON text and as structuredContent. Lookup misses return "did you mean" slug suggestions (prefix / substring / edit-distance ≤ 2 against the live product list).

Resources (resources/list / resources/read): llms.txt, the EOS Edge Device feed, Exploited & Unpatchable, KEV by product, the edge change log.

Prompts (prompts/list / prompts/get): audit_stack, eol_calendar, edge_device_review.

Endpoints: POST / (JSON-RPC), GET / (info page), GET /health (liveness JSON), GET /.well-known/mcp/server-card.json (discovery card).

Usage telemetry

With the USAGE Analytics Engine binding (see wrangler.toml, dataset endoflife_mcp_usage) each method / tool call writes one data point: tool name, client user agent, ok/error, keyed/anon, latency in ms. No request bodies. Query via the Cloudflare Analytics Engine SQL API, e.g.

SELECT blob1 AS tool, count() AS calls, sum(_sample_interval) AS weighted

FROM endoflife_mcp_usage WHERE timestamp > NOW() - INTERVAL '7' DAY GROUP BY tool ORDER BY calls DESC

The binding is optional; the code no-ops without it.

Deploy

Production deploys run from GitHub Actions, never a local wrangler:

gh workflow run mcp-server-deploy.yml

(.github/workflows/mcp-server-deploy.yml, pinned wrangler; needs the CLOUDFLARE_API_TOKEN / CLOUDFLARE_ACCOUNT_ID repository secrets.) Local wrangler dev still works for development; the API service binding and the USAGE dataset are declared for both the default and production environments.

Custom domain (mcp.endoflife.ai)

The route in wrangler.toml needs mcp.endoflife.ai to resolve through Cloudflare: an AAAA record, name mcp, IPv6 100::, proxied. Already in place.

Test before deploying

A Node harness exercises every method against the live API and feeds (the module runs unchanged in Node with env.API = { fetch }):

node scratch/mcp_test.mjs   # see the session scratchpad; 22 RPC calls, expects 0 failures

Offline unit tests (fetch mocked, no network): npm test in mcp-server/ (node --test test/).

Run as a container (Red Hat UBI)

server.mjs runs the same handler that serves mcp.endoflife.ai inside a plain Node.js process, and Dockerfile packages it on registry.access.redhat.com/ubi9/nodejs-22-minimal for cluster deploys (the form the OpenShift AI MCP catalog expects). No build step, no dependencies; the container talks to https://api.endoflife.ai over HTTPS and runs as the unprivileged UBI user (uid 1001).

docker build -t endoflife-mcp mcp-server/

docker run --rm -p 8080:8080 -e ENDOFLIFE_API_KEY=your_key endoflife-mcp curl -s localhost:8080/health

Endpoints are the Worker's own: POST / (Streamable HTTP JSON-RPC), GET /health (readiness), GET /.well-known/mcp/server-card.json. Set ENDOFLIFE_API_KEY (docker run -e ENDOFLIFE_API_KEY=...) and the server sends it as X-API-Key on every call that carries no key of its own. A self-hosted server needs it: the API does not answer data requests without a key, and only the hosted endpoint at mcp.endoflife.ai stays keyless. A free key is emailed at once from https://endoflife.ai/api#free-key (150 requests a day, no expiry; higher volume is on a paid key). Validated on RHEL 9 and 10 with Node 20 and 22 by .github/workflows/rhel-validation.yml (evidence in docs/company/redhat-validation-evidence.md).

Connect from an MCP client

Claude Desktop / Cursor / VS Code (mcpServers):

{

"mcpServers": { "endoflife": { "command": "npx", "args": ["mcp-remote", "https://mcp.endoflife.ai"] } } }

Clients with native remote-MCP support can use the URL directly:

{ "mcpServers": { "endoflife": { "url": "https://mcp.endoflife.ai" } } }

Test without a client

# tools/list

curl -s https://mcp.endoflife.ai -X POST -H 'Content-Type: application/json' \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' | jq

KEV exposure for a product

curl -s https://mcp.endoflife.ai -X POST -H 'Content-Type: application/json' \ -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"get_kev_exposure","arguments":{"product":"ivanti-connect-secure"}}}' | jq

health + discovery card

curl -s https://mcp.endoflife.ai/health | jq curl -s https://mcp.endoflife.ai/.well-known/mcp/server-card.json | jq

Auth & tiers

The read tools work with no key for individual use and evaluation through the hosted endpoint mcp.endoflife.ai (each agent gets 2,000 a day and 5 per call). Calling the API directly, or running this server yourself, needs a key for every data request (set ENDOFLIFE_API_KEY on a self-hosted server; a free key gives 150 requests a day and 5 components per call, from https://endoflife.ai/api#free-key). Agents that run inside a company's tooling, check inventories or call on a schedule are production use and belong on a paid key: Starter ($89/month, 10,000 requests a day, 25 per call) or Pro ($299/month, 100,000 requests a day under fair use, 50 per call), issued at checkout from https://endoflife.ai/api?utm_source=mcp#get-key. Forward it as an X-API-Key header; the Worker passes it straight through to api.endoflife.ai.

Notes

  • Same-zone trap: api.endoflife.ai is a Worker on this zone; a plain fetch() to it goes to origin and fails. The API service binding is mandatory in prod.
  • Static feeds are fetched from the site origin with cf.cacheTtl = 600 and memoised in the isolate for 10 minutes.
  • Per-client rate limits: relies on the upstream API's limits. If MCP traffic grows, add a KV rate-limiter keyed on CF-Connecting-IP before the upstream call.
  • Discovery card is also served from the main site at https://endoflife.ai/.well-known/mcp/server-card.json.