list_models
List models
List the AI video models VidFare tracks, with the cheapest current dollars per second for each.
無需輸入參數。

com.vidfare由 vidfare.com 發布官方發布者v1.0.0更新於 Nov 6, 2026
來自 VidFare 的唯讀 AI 影片價格、片段費用和優惠資訊。
AI 翻譯由 AI 模型根據下方的原文描述翻譯,可能有誤。
Read-only AI video prices, clip costs, and deals from VidFare.
VidFare 的託管 MCP 服務(mcp.vidfare.com),由 vidfare.com 發布;無需登入;Streamable HTTP;5 個工具。
暫無 AI 概覽:以下資訊來自註冊中心條目和服務本身。
Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。
把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。
閱讀 https://sourceweft.com/mcp/com.vidfare%2Fvidfare/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。把它新增到你客戶端的 mcpServers 設定中。
{
"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.
來源: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.
無需輸入參數。
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已滿足適用檢查項的 100%
該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。
CLOUDFLARE_ACCOUNT_ID=... CLOUDFLARE_API_TOKEN=... python3 scripts/mcp_usage.pycd mcp-servernpm installnpm testnpx wrangler dev