list_scenarios
List use-case scenarios
List the use-case scenarios (coding assistant, customer support bot, bulk classification, ...) that recommend_models ranks for.
无需输入参数。

io.github.yeaske由 GitHub 账号 yeaske 发布v0.1.3更新于 Nov 19, 2026
Recommend, compare and price AI models, and check retirement dates, from modelanalyzer.ai.
让助手基于 modelanalyzer.ai 的免费开放数据推荐、比较和估算 AI 模型价格,并查询模型下线日期。
Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。
参照 仓库 中的启动说明。
An MCP server that lets your coding assistant recommend, compare and price AI models, and check when they retire, using the free open data from AI Model Analyzer.
It runs locally over stdio and reads one public file, https://modelanalyzer.ai/data/summary.json, which the site rebuilds every night. There is no API key, no account and no server to host. Answers link back to the matching page on the site.
Add it to your assistant's MCP configuration:
For Claude Code:
Requires Node.js 20 or later.
Example prompts: "Which model should I use for a customer support bot under $100 a month?", "Compare Claude Opus 5.5 and GPT-6.1 Sol", "Is any model I use being retired soon?"
Numbers are exactly what modelanalyzer.ai shows, generated nightly. Cost per task and speed come from Artificial Analysis; Arena scores from LMArena (CC-BY 4.0). See the methodology and open data pages.
The summary is cached in memory for six hours. Set MODELANALYZER_BASE_URL to read from another host: https only, or plain http to localhost for a local build.
The server only reads: it runs no commands, touches no files, opens no ports and sends nothing about you. It downloads one public file and treats it as untrusted before any of it reaches your assistant: the structure is checked, text is stripped of control and invisible characters and capped in length, ids are limited to a safe alphabet, links must be on the site it read from, and the download is limited to 15 seconds and 5 MB. Report security issues privately through GitHub's "Report a vulnerability" on this repository.
Bug reports and ideas are welcome in issues. The rankings and numbers themselves come from the site; see its methodology.
Bump the version in package.json, server.json (twice) and src/server.js; npm test checks they agree. Then:
The second step lists the new version in the MCP Registry as io.github.yeaske/modelanalyzer-mcp.
MIT, © Digital Designs Now.
来源:README.md,提交 b143b28
List use-case scenarios
List the use-case scenarios (coding assistant, customer support bot, bulk classification, ...) that recommend_models ranks for.
无需输入参数。
Recommend models for a use case
AI Model Analyzer's current ranking for a use-case scenario, blending benchmark quality with cost at a typical workload. Optionally filter by a monthly budget at that workload or by open weights.
limitscenario必填openWeightsOnlymaxMonthlyCostUSDSearch models
Find models by name, id or maker. Returns ids for the other tools, plus Analyzer Index, price, cost per task, speed and context.
limitquery必填Compare models
Side-by-side table of 2 to 6 models: Analyzer Index and rank, input/output price, cost per task, speed, time to first token, context, open weights and announced retirement.
models必填Estimate API cost
Cost per request, day and month for a model at list price, given tokens per request and requests per day.
model必填inputTokens必填outputTokens必填requestsPerDayUpcoming model retirements
Announced API shutdown dates for tracked models, with each maker's recommended replacement.
无需输入参数。
已满足适用检查项的 80%
该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。
请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。
请在仓库或注册中心条目中声明许可证。

tools.model官方发布者
零认证远程工具服务器,为智能体提供一次性邮箱验证码读取、持久检查点、Webhook 收件箱、定时唤醒、任务回执与网页转 Markdown。
ai.com.nlp官方发布者
搜索精选的开放权重AI模型发布、许可证、架构和原始来源。AI 翻译

foundation.uor.hub官方发布者
一个远程 MCP 服务器,让助手搜索开放模型索引,并获取带 SHA-256 校验值的下载链接。

由 GitHub 账号 Greatbeing 发布
探测兼容 OpenAI 的网关,记录延迟与成功率历史,并对模型排名或推荐,帮助助手选出真正可用的模型。

由 GitHub 账号 Sagargupta16 发布
让助手通过一个 AWS 账户调用、对比和评审多种 Bedrock 文本模型,并生成或编辑图像、视频和向量嵌入。
{ "mcpServers": { "modelanalyzer": { "command": "npx", "args": ["-y", "modelanalyzer-mcp"] } }}claude mcp add modelanalyzer -- npx -y modelanalyzer-mcpnpm installnpm testnpm publishmcp-publisher login githubmcp-publisher publish