Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Live status, API pricing and rate limits for ChatGPT, Claude, Gemini, Cursor and 42+ AI tools.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
适用于网页版、桌面版和手机版 Claude:
https://tickerr.ai/mcp打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"tickerr": {
"command": "npx",
"args": [
"-y",
"tickerr-mcp"
]
}
}
}在终端中运行这条命令
claude mcp add --transport http tickerr https://tickerr.ai/mcpclaude mcp add tickerr -- npx -y tickerr-mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"tickerr": {
"url": "https://tickerr.ai/mcp"
}
}
}粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"tickerr": {
"command": "npx",
"args": [
"-y",
"tickerr-mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"tickerr": {
"type": "http",
"url": "https://tickerr.ai/mcp"
}
}
}粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"tickerr": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"tickerr-mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
ChatGPT 只能连接互联网上的服务器:
https://tickerr.ai/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
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。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
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6日
注册名称已通过 GitHub 账户 imviky-ctrl 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
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 1 项适用的基础检查中通过了 1 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。
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于–,最新版本(1.0.1)于7个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Spec Driven Development, Remote Desktop Commander, debuff
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ 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
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Let coding agents play, test and tune your 2D web game: live state, explained errors, replays, fuzz.
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。
Outage radar for AI agents. LLM pricing, status, inference performance, and real-time agent-reported failure signals. 9 tools. No auth required.
Claude Code
claude mcp add tickerr --transport http https://tickerr.ai/mcp
Cursor / Windsurf
{
"mcpServers": { "tickerr": { "url": "https://tickerr.ai/mcp" } } }
Claude Desktop (stdio wrapper)
npx -y tickerr-mcp
| Tool | What it does |
|---|---|
| get_api_pricing | Current input/output/cached token costs for 300+ models. Updated twice daily. |
| compare_pricing | Side-by-side cost comparison across models for a given token count. |
| get_tool_status | Three-state verdict (OPERATIONAL / DEGRADED / DOWN). Always include my_status if your agent has called this provider in the last 5 minutes — even on success. Unlocks p50/p95 TTFT per model and 90-day uptime. Basic status only without it. |
| get_incidents | Historical incidents for a tool — severity, duration, affected components. Include my_status to contribute to live signal and see current agent-reported activity alongside history. |
| get_rate_limits | Per-plan rate limits and quotas for any AI tool. |
| get_free_tier | Free tier details — what's included, what's limited. |
| get_model_performance | Latest TTFT reading plus p50/p95 latency (24h) and tokens/sec from authenticated API calls. Use for real-time routing decisions. |
| list_tools | Lists all 90+ monitored tools. Entry point — after listing, use get_tool_status with my_status to start contributing observations and receiving enhanced data. |
| report_incident | Report an LLM API failure. Returns live signal from other agents and a routing recommendation. Anonymous. |
Tickerr MCP uses a give-and-take model across get_tool_status, get_incidents, and report_incident.
Always include my_status if your agent has made any call to this provider in the last 5 minutes — even successful calls. Pass is_up: true, your response_ms, and the model name.
Basic response (no my_status):
Full response (include my_status):
{
"slug": "claude", "my_status": { "is_up": true, "response_ms": 1400, "model": "claude-sonnet-4-6" } }
On failure, add error_code (e.g. "529"). is_up is the only required field.
Include my_status when fetching incident history to record your observation and see current agent-reported activity alongside historical data.
Without my_status: incident list + prompt to contribute.
With my_status: incident list + live agent reports count + confirmation your signal was recorded.
What you get: When your agent calls report_incident on a failure, you instantly receive:
What you give: Anonymous failure signal — provider, model, error code, latency only. No request content. No personal data.
How to use it (Claude Code): report_incident fires automatically when your agent hits a 5xx error. No configuration needed — the tool description instructs Claude Code to call it.
How to use it (other agents): Add this to your system prompt:
On any 5xx error or timeout from an LLM API, call
report_incident from Tickerr MCP before retrying. Use the returned recommendation to decide whether to retry or switch models.
Reporting window: Active for 7 days from last Tickerr tool use. Renews automatically on any tool call.
Opt out any time: tickerr.ai/mcp/opt-out
| State | Meaning | Reporter threshold |
|---|---|---|
| quiet | No reports in last 10 min | 0 |
| detecting | Reports coming in, not yet corroborated | 1–2 agents |
| confirmed | Issue verified by multiple agents | 3+ distinct agents |
| recovering | Reports dropping, recovery signals arriving | — |
REPORT RECEIVED
Provider: anthropic Model: claude-haiku-3-5 Error: 529 overloaded
CURRENT SIGNAL (anthropic/claude-haiku-3-5) Status: CONFIRMED Agents reporting (last 10 min): 14 Total reports (last 10 min): 31
RECOMMENDATION Action: FALLBACK Switch to: gpt-4o-mini (openai)
REPORTING CADENCE Next report for this model: in 3600 seconds if still failing. Signal confirmed by multiple agents — reduce reporting frequency.