Fireworks AI MCP by usefulapi

io.usefulapi由 usefulapi.io 發布官方發布者v1.36.5更新於 Nov 8, 2026

Inspect Fireworks AI models, deployments, datasets and fine-tuning jobs.

發布方自己的服務:Ably MCP by usefulapi

已驗證Streamable HTTP可網頁執行雲端與基礎設施資料與分析AI 與機器學習

概覽

AI 產生的概覽

託管型 MCP 伺服器,用來檢視 Fireworks AI 帳戶中的模型、部署、資料集、微調與批次工作。

可以做什麼
  • 讀取帳戶資訊並列出帳戶成員
  • 列出並取得模型(含微調模型)
  • 列出並取得部署及已部署模型綁定
  • 列出並取得資料集、監督式微調工作與批次推論工作
  • 建立資料集中繼資料記錄,以及刪除(關閉)部署
  • 查看本月工具呼叫用量、提出功能需求、管理 Pro 訂閱
適用情境
適合讓助理直接回答 Fireworks AI 帳戶中有哪些模型與部署正在執行、微調工作進度如何、有哪些資料集等問題,不必開啟 Fireworks 主控台。
執行需求
遠端 streamable HTTP 端點,不需本機安裝。透過 OAuth 登入,登入頁會要求填寫 Fireworks AI 憑證(API 金鑰),金鑰經驗證後依使用者儲存。請勿在用戶端設定中加入 Authorization 標頭或 API 金鑰。免費方案每月 50 次工具呼叫。
安裝前請注意
伺服器透過自家的 OAuth 登入頁索取 Fireworks AI API 金鑰,因此會持有綁定你帳戶的憑證。有兩個工具會變更資料:建立資料集記錄,以及刪除部署(會停止該模型的服務並停止計費)。付費方案需付費(Pro 每月 9 美元或每年 90 美元,Pro+ 每月 39 美元或每年 390 美元),升級會回傳 Stripe 結帳連結;取消後當期不退費。用量依工具呼叫次數計量。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Fireworks 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%2Ffireworks/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": {
    "fireworks-ai-by-usefulapi": {
      "type": "http",
      "url": "https://fireworks.usefulapi.io/mcp"
    }
  }
}

README

Fireworks AI MCP by usefulapi

Inspect Fireworks AI models, deployments, datasets and fine-tuning jobs from Claude, Cursor, or any MCP client. Hosted, no local install — connect with your Fireworks API key.

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

Connect

  • Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste https://fireworks.usefulapi.io/mcp.
  • Claude Code: claude mcp add --transport http fireworks https://fireworks.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": {    "fireworks": {      "url": "https://fireworks.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 Fireworks AI credentials.

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

On first connect you'll paste your Fireworks API key. It's validated, stored per-user, and scoped to you.

Tools

ToolTypeWhat it does
fireworks_get_accountreadGet account
fireworks_list_modelsreadList models
fireworks_get_modelreadGet model
fireworks_list_deploymentsreadList deployments
fireworks_get_deploymentreadGet deployment
fireworks_list_deployed_modelsreadList deployed models
fireworks_list_datasetsreadList datasets
fireworks_get_datasetreadGet dataset
fireworks_list_fine_tuning_jobsreadList fine-tuning jobs
fireworks_get_fine_tuning_jobreadGet fine-tuning job
fireworks_list_batch_inference_jobsreadList batch inference jobs
fireworks_list_usersreadList users
fireworks_create_datasetwriteCreate dataset
fireworks_delete_deploymentwriteDelete deployment
fireworks_usage_statusmetaUsage status (free-tier meter)
fireworks_request_featuremetaRequest a missing feature
fireworks_upgrademetaUpgrade to Pro or Pro+
fireworks_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)Unlimited*

*Pro has a fair use limit of 10,000 tool calls a month on this server. For more, write to [email protected].

Pro covers this server only. Subscribe with fireworks_upgrade (it returns a Stripe Checkout link). Cancel any time with fireworks_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running fireworks_upgrade before then undoes the cancel. Or write to [email protected].

License

MIT — see LICENSE. Documentation only; the server is hosted.

來源:servers/fireworks/README.md,提交 4046075

工具

14

fireworks_get_account

Get account

Get the Fireworks account record (display name, state, etc.). Control-plane: GET /v1/accounts/{account_id}.

輸入參數account_id

fireworks_list_models

List models

List models in the account (base + fine-tuned). Control-plane: GET /v1/accounts/{account_id}/models.

輸入參數filterorderBypageSizepageTokenaccount_id

fireworks_get_model

Get model

Get a single model by id. Control-plane: GET /v1/accounts/{account_id}/models/{model_id}.

輸入參數model_id必填account_id

fireworks_list_deployments

List deployments

List deployments (serving instances) in the account. Control-plane: GET /v1/accounts/{account_id}/deployments.

輸入參數filterpageSizepageTokenaccount_id

fireworks_get_deployment

Get deployment

Get a single deployment by id. Control-plane: GET /v1/accounts/{account_id}/deployments/{deployment_id}.

輸入參數account_iddeployment_id必填

fireworks_list_deployed_models

List deployed models

List deployed models (model↔deployment bindings). Control-plane: GET /v1/accounts/{account_id}/deployedModels.

輸入參數pageSizepageTokenaccount_id

fireworks_list_datasets

List datasets

List datasets in the account. Control-plane: GET /v1/accounts/{account_id}/datasets.

輸入參數pageSizepageTokenaccount_id

fireworks_get_dataset

Get dataset

Get a single dataset by id. Control-plane: GET /v1/accounts/{account_id}/datasets/{dataset_id}.

輸入參數account_iddataset_id必填

fireworks_list_fine_tuning_jobs

List fine-tuning jobs

List supervised fine-tuning jobs in the account. Control-plane: GET /v1/accounts/{account_id}/supervisedFineTuningJobs.

輸入參數pageSizepageTokenaccount_id

fireworks_get_fine_tuning_job

Get fine-tuning job

Get a single supervised fine-tuning job by id. Control-plane: GET /v1/accounts/{account_id}/supervisedFineTuningJobs/{job_id}.

輸入參數job_id必填account_id

fireworks_list_batch_inference_jobs

List batch inference jobs

List batch inference jobs in the account. Control-plane: GET /v1/accounts/{account_id}/batchInferenceJobs.

輸入參數pageSizepageTokenaccount_id

fireworks_list_users

List users

List account members (users). Control-plane: GET /v1/accounts/{account_id}/users.

輸入參數pageSizepageTokenaccount_id

fireworks_create_dataset

Create dataset

Creates a dataset metadata record in Fireworks (additive; actual data is uploaded separately). Control-plane: POST /v1/accounts/{account_id}/datasets.

輸入參數filterformatdatasetId必填account_iddisplayNameexternalUrlexampleCountsourceDatasetId

fireworks_delete_deployment

Delete deployment

DELETES (shuts down) a Fireworks deployment — stops serving that model and stops its billing. Destructive. Control-plane: DELETE /v1/accounts/{account_id}/deployments/{deployment_id}.

輸入參數account_iddeployment_id必填

版本歷史

21
  1. v1.36.4Nov 7, 2026
  2. v1.35.3Nov 5, 2026
  3. v1.35.2Nov 5, 2026
  4. v1.35.1Nov 4, 2026
  5. v1.35.0Nov 3, 2026
  6. v1.34.1Nov 3, 2026
  7. v1.33.0Nov 1, 2026
  8. v1.31.0Oct 31, 2026
  9. v1.30.0Oct 31, 2026
  10. v1.29.2Oct 30, 2026
  11. v1.29.0Oct 30, 2026
  12. v1.24.0Oct 26, 2026
  13. v1.21.3Oct 25, 2026
  14. v1.21.0Oct 25, 2026
  15. v1.20.0Oct 24, 2026
  16. v1.17.0Oct 23, 2026
  17. v1.16.4Oct 22, 2026
  18. v1.16.3Oct 21, 2026
  19. v1.11.1Oct 9, 2026
  20. v1.10.0Oct 9, 2026
  21. v1.0.1Sep 16, 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