list_models
List models
List the AI video models VidFare tracks, with the cheapest current dollars per second for each.
无需输入参数。

com.vidfare由 vidfare.com 发布官方发布者v1.0.0更新于 Nov 6, 2026
来自 VidFare 的只读 AI 视频价格、片段费用和优惠信息。
AI 翻译由 AI 模型根据下方的原文描述翻译,可能有误。
Read-only AI video prices, clip costs, and deals from VidFare.
VidFare 的托管 MCP 服务(mcp.vidfare.com),由 vidfare.com 发布;无需登录;Streamable HTTP;5 个工具。
暂无 AI 概览:以下信息来自注册中心条目和服务本身。
Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。
把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。
阅读 https://sourceweft.com/mcp/com.vidfare%2Fvidfare/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。把它添加到你客户端的 mcpServers 配置中。
{
"mcpServers": {
"vidfare": {
"type": "http",
"url": "https://mcp.vidfare.com/mcp"
}
}
}Public, read-only Model Context Protocol server for the VidFare price catalog. It speaks Streamable HTTP at /mcp, with no authentication. A client such as ChatGPT, Claude, or Cursor can list models, read prices, estimate a clip, and list deals. Every result includes the VidFare source URL, the last-checked date, and a vidfare.com page link. Those vidfare.com links also carry utm_source=mcp&utm_medium=tool&utm_campaign=vidfare_mcp.
The Worker is live at https://mcp.vidfare.com/mcp. Do not run wrangler login or wrangler deploy from this repository.
The Worker fetches only:
https://vidfare.com/data/prices.jsonhttps://vidfare.com/deals.json (the same JSON is also published at /data/deals.json)Responses are cached for 5 minutes. If a fetch fails, or the catalog does not state a price for the request, the tool says so and does not fill in a number.
estimate_cost uses the same row filter as the credit calculator (scripts/variations.py) and the same plan math as the calculator script: plan price ÷ credits × credits per clip, divided again by the share of credits actually used. API rows are billed seconds times the stated dollars per second. scripts/test_mcp_parity.py checks that against the site code.
A tools/call writes one Workers Analytics Engine point: blob1 is the tool name (unknown if it is not one of the five tools), blob2 is success or error, and double1 is 1. The engine stores the time. The UTC day is that timestamp. The read script also prints when that UTC midnight falls in Pacific Time. Nothing else is stored: no arguments, prompt, IP address, user agent, session id, or country. There is no public stats URL.
Counts are tool requests, not unique people, visits, or sponsor impressions. A retry, a second call from the same person, and a client that does not send the test header each add one. Requests with X-VidFare-Test: 1, and POSTs to localhost or 127.0.0.1 (wrangler dev), are not written. initialize, tools/list, notifications, OPTIONS, and GET are not written. A crawler or someone else's test client that calls a tool is counted.
The write is not awaited and a failure is ignored, so a counter error does not change the tool response.
wrangler.jsonc binds USAGE to the dataset vidfare_mcp_usage. The dataset is created on the first write. Deploying that binding uses the existing Worker deploy token (Workers Scripts Edit or Workers Admin, Workers Routes Edit, and Zone Read). It does not need Analytics Read. Reading the counts does. Create a separate token with Account → Account Analytics → Read, scoped to the VidFare account, and run:
Do not put that token in the repo.
wrangler dev stays on this machine. It does not deploy.
Cursor can use mcp-server/.mcp.json. Put the same JSON in a project's .cursor/mcp.json. The URL is https://mcp.vidfare.com/mcp.
server.json is the MCP Registry document. The name is com.vidfare/vidfare. The remote is streamable-http at https://mcp.vidfare.com/mcp.
Namespace verification for com.vidfare is HTTP. The site serves the published proof record at https://vidfare.com/.well-known/mcp-registry-auth. The file is one line, v=MCPv1; k=ed25519; p=<public key>. The private key is not in this repo.
The site build copies the file into dist/.well-known/ and writes dist/.nojekyll. actions/upload-pages-artifact leaves dot paths out unless include-hidden-files is true. Both deploy workflows set that, so the URL answers 200 with no redirect.
Token, one Cloudflare account (the account that owns vidfare.com) and one zone (vidfare.com only):
Do not add Workers KV, R2, Tail, Account Settings, DNS, or user membership permissions. The Worker has no bindings.
DNS record on vidfare.com, created in the dashboard (the token above does not edit DNS):
That is the proxied hostname a Worker custom domain uses. wrangler.jsonc sets the route to custom domain mcp.vidfare.com. After the record exists, npx wrangler deploy from this directory publishes the Worker. It still needs CLOUDFLARE_API_TOKEN in the environment, not in the repo.
来源:mcp-server/README.md,提交 f3260aa
List models
List the AI video models VidFare tracks, with the cheapest current dollars per second for each.
无需输入参数。
Get model prices
List current VidFare prices for one model. provider and resolution are optional filters. Prices the catalog does not contain are omitted rather than guessed.
model必填providerresolutionEstimate clip cost
Cost of one clip from the VidFare calculator. Credit-plan rows use plan price ÷ credits × credits per clip, then the percent of credits used. API rows are billed seconds times the stated dollars per second. A length, resolution, audio value, or input the vendor page does not state is returned without a price.
planusedaudioinputmodel必填seconds必填providerresolutionapply_dealswindow_secondsCheapest options
Cheapest stated VidFare price for a clip length and resolution, overall and per model. Rows the vendor does not state for that length or resolution are omitted.
usedaudioinputseconds必填resolution必填apply_dealsList deals
List VidFare deals copied from vendor pages and official accounts. status is live, upcoming, ended, or all. Defaults to live. An end date is included only when the source stated one.
status已满足适用检查项的 100%
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。
CLOUDFLARE_ACCOUNT_ID=... CLOUDFLARE_API_TOKEN=... python3 scripts/mcp_usage.pycd mcp-servernpm installnpm testnpx wrangler dev