fal.ai MCP by usefulapi

io.usefulapi由 usefulapi.io 發布官方發布者v1.39.2更新於 Nov 14, 2026

Run fal.ai models, poll the inference queue and read model schemas.

發布方自己的服務：Ably MCP by usefulapi

已驗證Streamable HTTP可網頁執行媒體與設計AI 與機器學習

概覽

AI 產生的概覽

託管型 MCP 伺服器，讓助理列出 fal.ai 模型、讀取模型輸入結構、執行推論並輪詢請求結果。

可以做什麼
  • 列出可用的 fal.ai 模型並讀取各模型的輸入結構
  • 提交推論請求、以訂閱方式執行模型、取消請求
  • 查詢請求狀態並取得已完成的請求結果
  • 查看本月工具呼叫用量並提交功能請求
  • 升級付費方案或取消 Pro 訂閱
適用情境
適合讓助理生成圖片或影片、執行其他 fal.ai 模型，而不必自行撰寫 API 程式碼。也適合在提交工作前先了解有哪些模型以及它們需要哪些輸入。
執行需求
遠端 streamable HTTP 端點，無需本機安裝。只要填入伺服器網址連線，接著透過 OAuth 以 fal.ai 憑證登入，憑證會驗證並依使用者儲存。免費方案每月 50 次工具呼叫；付費方案透過 Stripe Checkout 結帳。
安裝前請注意
寫入類工具會提交、執行與取消 fal.ai 請求，可能消耗 fal.ai 額度並產生費用，執行前應先確認。登入頁會要求填寫 fal.ai 憑證，請只在官方登入流程中輸入。付費方案透過 Stripe 扣款，升級會立即按比例收取差額，取消後當期不退款。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 fal.ai MCP by usefulapi，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

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。

交給代理程式安裝

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/io.usefulapi%2Ffalai/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。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "fal-ai-by-usefulapi": {
      "type": "http",
      "url": "https://falai.usefulapi.io/mcp"
    }
  }
}

README

fal.ai MCP by usefulapi

Run fal.ai models, poll the inference queue and read model schemas. Hosted, no local install.

Live endpoint: https://falai.usefulapi.io/mcp · Homepage: https://usefulapi.io

Connect

  • Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste https://falai.usefulapi.io/mcp.
  • Claude Code: claude mcp add --transport http falai https://falai.usefulapi.io/mcp, then run /mcp to log in.
  • VS Code: Add to VS Code.
  • Cursor and other clients: add the URL as a remote MCP server:
json
{  "mcpServers": {    "falai": {      "url": "https://falai.usefulapi.io/mcp"    }  }}

Add only the URL. Do not add an Authorization header or an API key to the client config: the server signs you in with OAuth, and the login page asks for your fal.ai credentials.

Step-by-step setup, where to find your credentials, and FAQ: https://usefulapi.io/falai/

On first connect you'll paste your fal.ai credentials. They are validated, stored per-user, and scoped to you — no keys in config files.

Tools

ToolTypeWhat it does
falai_list_modelsreadList models
falai_get_model_schemareadGet model schema
falai_get_request_statusreadGet request status
falai_get_request_resultreadGet request result
falai_submit_requestwriteSubmit request
falai_run_modelwriteRun model (subscribe)
falai_cancel_requestwriteCancel request
falai_usage_statusmetaUsage status (free-tier meter)
falai_request_featuremetaRequest a missing feature
falai_upgrademetaUpgrade to Pro or Pro+
falai_cancel_subscriptionmetaCancel the Pro subscription

read tools are read-only; write tools mutate data (clients should confirm them); meta tools report usage, manage your subscription or send a feature request.

Pricing

PlanPriceLimit
Free$050 tool calls / month
Pro$9/mo or $90/yr (2 months free)10,000 tool calls / month
Pro+$39/mo or $390/yr (2 months free)100,000 tool calls / month

Each paid plan covers this server only. Ask your AI to run falai_upgrade and choose Pro or Pro+, billed monthly or yearly (it returns a Stripe Checkout link). If you already have Pro, ask to change it to Pro+. The change requires your confirmation, keeps your billing interval and charges the price difference for the rest of the period immediately. Cancel any time with falai_cancel_subscription: your paid plan continues to the end of the paid period, with no refund for the current period, and asking to resume the same plan with falai_upgrade before then undoes the cancel. Or write to [email protected].

License

MIT

來源：servers/falai/README.md，提交 f22f848

工具

7

falai_list_models

List models

List or search fal.ai models in the registry (paginated). fal.ai API: GET /models (query: keywords, page, total).

輸入參數pagetotalkeywords

falai_get_model_schema

Get model schema

Get the OpenAPI 3 schema for a model — its input/output fields (components.schemas). Use this to learn what inputs a model accepts before submitting. fal.ai API: GET /openapi/queue/openapi.json?endpoint_id={model_id}.

輸入參數model_id必填

falai_get_request_status

Get request status

Get the status of a queued request (IN_QUEUE | IN_PROGRESS | COMPLETED). fal.ai queue: GET {queue}/{model_id}/requests/{request_id}/status (optional logs=1).

輸入參數logsmodel_id必填request_id必填

falai_get_request_result

Get request result

Get the final output of a COMPLETED queued request. fal.ai queue: GET {queue}/{model_id}/requests/{request_id}.

輸入參數model_id必填request_id必填

falai_submit_request

Submit request

Submit an inference request to the queue and return immediately (async — does NOT wait for completion). Returns { request_id, response_url, status_url, cancel_url, queue_position }. Consumes fal credits when the model runs. fal.ai queue: POST {queue}/{model_id} with body = the model input.

輸入參數input必填model_id必填

falai_run_model

Run model (subscribe)

Convenience 'subscribe': submit a request, poll its status until COMPLETED, then return the result. Consumes fal credits. If it does not complete within the wait budget, returns a { status, request_id, status_url, note } object (NOT an error) so you can keep polling with falai_get_request_status / falai_get_request_result.

輸入參數input必填model_id必填max_wait_secondspoll_interval_seconds

falai_cancel_request

Cancel request

Request cancellation of a queued (not-yet-started) request. Returns 202 { status: 'CANCELLATION_REQUESTED' }. fal.ai queue: PUT {queue}/{model_id}/requests/{request_id}/cancel.

輸入參數model_id必填request_id必填

版本歷史

26
  1. v1.39.2最新Nov 14, 2026
  2. v1.39.1Nov 13, 2026
  3. v1.38.0Nov 12, 2026
  4. v1.37.3Nov 11, 2026
  5. v1.36.5Nov 8, 2026
  6. v1.36.4Nov 7, 2026
  7. v1.35.3Nov 5, 2026
  8. v1.35.2Nov 5, 2026
  9. v1.35.1Nov 4, 2026
  10. v1.35.0Nov 3, 2026
  11. v1.34.1Nov 3, 2026
  12. v1.33.0Nov 1, 2026
  13. v1.31.0Oct 31, 2026
  14. v1.30.0Oct 31, 2026
  15. v1.29.2Oct 30, 2026
  16. v1.29.0Oct 30, 2026
  17. v1.24.0Oct 26, 2026
  18. v1.21.3Oct 25, 2026
  19. v1.21.0Oct 25, 2026
  20. v1.20.0Oct 24, 2026
  21. v1.17.0Oct 23, 2026
  22. v1.16.4Oct 22, 2026
  23. v1.16.3Oct 21, 2026
  24. v1.11.1Oct 9, 2026
  25. v1.10.0Oct 9, 2026
  26. v1.0.0Sep 29, 2026

評分

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。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

其他 Usefulapi 整合

Ably MCP by usefulapi

io.usefulapi官方發布者

針對 Ably 的託管 MCP 伺服器，讓助理檢視頻道、線上狀態與用量統計、發布訊息，並查看應用程式設定。

Streamable HTTP可網頁執行
溝通與協作15 個工具Nov 14, 2026

ROLLER MCP by usefulapi

io.usefulapi官方發布者

唯讀存取 ROLLER 場館資料：搜尋預訂、查詢產品可用性，並查看賓客、免責聲明、禮品卡與每日報表。

Streamable HTTP可網頁執行
資料與分析42 個工具Nov 14, 2026

Planerio MCP by usefulapi

io.usefulapi官方發布者

託管的 Planerio 連接器，讓助理讀取排班、人力需求、可用人員、員工資料、缺勤與年假天數。

Streamable HTTP可網頁執行
效率與工作流6 個工具Nov 14, 2026

Marmin MCP by usefulapi

io.usefulapi官方發布者

唯讀存取 Marmin 的阿聯酋電子發票資料：發票、貸項通知單、UBL XML、Peppol 狀態與業務檔案。

Streamable HTTP可網頁執行
金融10 個工具Nov 14, 2026

Oyster MCP by usefulapi

io.usefulapi官方發布者

面向 Oyster 的遠端 MCP 伺服器，讓助理讀取團隊、休假、費用、合約與發票資料，並核准或拒絕相關申請。

Streamable HTTP可網頁執行
效率與工作流20 個工具Nov 14, 2026