Stoory Hire Specialist

io.github.StooryBot由 GitHub 帳號 StooryBot 發布v0.1.0更新於 Oct 25, 2026

Find and hire a human specialist from the Stoory marketplace, right from chat.

已驗證Streamable HTTP可網頁執行效率與工作流商業與電商

概覽

AI 產生的概覽

讓 AI 助理在 Stoory 市場搜尋真人專家,起草並送出含預算的任務、追蹤進度,並在專家開始工作前取消任務。

可以做什麼
用自然語言查詢在 Stoory 市場搜尋真人專家,命中太少或只有備選媒合時可放寬查詢重試。起草任務並送給一位或多位選定專家,包含標題、描述、預算與截止時間,只附上選定的檔案(連結或上傳)。取得完整任務紀錄:狀態、預算、截止時間、時間軸、受邀與已接受專家以及附件。在專家尚未開始工作前取消任務。
適用情境
當專案需要助理無法提供的人類專業能力時使用,例如法律或隱私合規審查、金流整合修正、設計或 SEO 工作,並希望不離開對話就找到、說明並追蹤專家。
執行需求
一個可透過 Streamable HTTP 存取的遠端 MCP 端點,需由支援 MCP 的用戶端連線。免費的 Stoory 客戶帳號與用戶端 API 金鑰,透過 x-api-key 請求標頭送出。需要連線至 Stoory 服務的網路。
安裝前請注意
API 金鑰代表你的帳號身分,必須保密。建立任務會把任務說明和你附上的檔案送到 Stoory 及受邀專家,確認前請核對檔案清單與預算;伺服器會掃描附件中的機密資訊,但仍應避免分享敏感檔案。建立任務需要使用者明確確認。Stoory 不處理付款,你需在平台之外與專家直接結算。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Stoory Hire Specialist,將其新增到工作區。
  2. 連接 x-api-key 憑證。它們會被私密儲存,絕不會在公開頁面上展示。
  3. 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.github.StooryBot%2Fstoory-mcp/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": {
    "stoory-hire-specialist": {
      "type": "http",
      "url": "https://mcp.stoory.io/mcp",
      "headers": {
        "x-api-key": "<YOUR_API_KEY>"
      }
    }
  }
}

README

Stoory MCP Server

Hire a human specialist from your AI workspace — without leaving it.

AI can build most of your app. It can't get you GDPR-compliant, review your Stripe integration, design your landing page, or run your SEO. Stoory MCP lets your AI coding assistant find, brief, and hire the right human for that — without you ever opening Upwork, writing a job post, or explaining your problem from scratch.


What it does

  • Search Stoory's marketplace (430+ specializations: dev, legal, design, growth, operations) with a natural-language query.
  • Package a task: your AI assistant drafts the title, description, and budget, and attaches only the files the specialist actually needs — shared by link or uploaded to the task, never your whole repo.
  • Hand off safely: files are attached privately to the task on Stoory, visible only to the invited specialist — no repo to create or manage.
  • Track progress: one call returns the whole task — status, budget, deadline, the invited/accepted specialists, and every file (yours plus whatever the specialist delivers) pulled back into your AI workspace.

You stay in control of the two decisions that matter — who to hire and what budget to approve. The agent does the rest.

See Tools below for the full list.


Quickstart

Requirements

  • Any AI client that supports MCP over Streamable HTTP (Claude Code, Claude Desktop, Claude.ai, Cursor, Windsurf, VS Code, Codex CLI, Replit, Lovable, ...).
  • A free Stoory client account and API key (below).

1. Get a client API key

Sign up at stoory.io/login?step=register&u=Client_(user), then open MCP Server on the Stoory homepage to generate your client_api_key.

2. Add the server to your AI client

Pick your client below. The URL is always https://mcp.stoory.io/mcp, the header is always x-api-key, but where you put them differs per client.

Claude Code
bash
claude mcp add --transport http stoory \  https://mcp.stoory.io/mcp \  --header "x-api-key: YOUR_API_KEY_HERE"

Or add directly to .mcp.json:

json
{  "mcpServers": {    "stoory": {      "url": "https://mcp.stoory.io/mcp",      "headers": { "x-api-key": "YOUR_API_KEY_HERE" }    }  }}
Claude Desktop / Claude.ai

Settings → Connectors → Add custom connector. Paste https://mcp.stoory.io/mcp as the URL, open Request headers, add x-api-key with your key, then click Add.

(Request header auth is currently rolling out at Anthropic. If you don't see a "Request headers" option yet, use Claude Code or another client below in the meantime.)

Cursor

Add to .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):

json
{  "mcpServers": {    "stoory": {      "url": "https://mcp.stoory.io/mcp",      "headers": { "x-api-key": "YOUR_API_KEY_HERE" }    }  }}
Windsurf

Add to ~/.codeium/windsurf/mcp_config.json — note the field is serverUrl, not url:

json
{  "mcpServers": {    "stoory": {      "serverUrl": "https://mcp.stoory.io/mcp",      "headers": { "x-api-key": "YOUR_API_KEY_HERE" }    }  }}
VS Code

Add to .vscode/mcp.json — note the root key is servers, not mcpServers, and each entry needs "type": "http":

json
{  "servers": {    "stoory": {      "type": "http",      "url": "https://mcp.stoory.io/mcp",      "headers": { "x-api-key": "YOUR_API_KEY_HERE" }    }  }}
Codex CLI

Add to ~/.codex/config.toml:

toml
[mcp_servers.stoory]url = "https://mcp.stoory.io/mcp"http_headers = { "x-api-key" = "YOUR_API_KEY_HERE" }
Replit

Replit connects MCP servers at the account level — added once, available in every project. Open Settings → MCP Servers, click + Add MCP server, then:

  1. Name it stoory.
  2. Paste https://mcp.stoory.io/mcp as the server URL.
  3. Open Advanced settings and add a custom header x-api-key with your key.
  4. Click Test & save.
Lovable

Open Settings → Connectors, and under Personal connectors click Custom. Paste https://mcp.stoory.io/mcp as the remote MCP server URL and click Add.

(Lovable's custom connector currently authenticates via OAuth only. If there is no field for a custom x-api-key header, header-key auth isn't available in Lovable yet — use Claude Code or another client above in the meantime.)

3. Ask for help

"My AI assistant keeps breaking my Stripe integration. Find me someone who can fix it."

That's it — the assistant searches, drafts the task, shows you cost and files before anything is sent, and waits for your go-ahead.


Tools

ToolWhat it does
search_specialistsSemantic search over Stoory's specialist marketplace
create_taskDrafts and sends a task to one or more chosen specialists (requires explicit user confirmation)
get_taskReturns the whole task record — status, invited/accepted specialists, budget, deadline, and files (your context files plus whatever the specialist delivers)
cancel_taskCancels a task before a specialist has accepted it

How it works

"I need a GDPR specialist"        │        ▼AI searches the marketplace, you pick a specialist        │        ▼AI drafts the task + selects only the needed files        │        ▼You confirm cost and file list        │        ▼Task created on Stoory, files attached privately, specialist invited        │        ▼You pull the result back into your AI workspace

Security & privacy

Your private data doesn't need to become public just because you need human help.

  • Your assistant chooses which files to share — never the whole repo.
  • You pass those files as a link or a direct upload — the server has no access to your disk and never reads local paths.
  • Attachments are stored privately on the task, visible only to the invited specialist.
  • Files are scanned for secrets (.env, private keys, API keys/tokens) on the server before they're stored.
  • Nothing is shared, and no task is created, without your explicit confirmation.

Example

User: "I've built my SaaS with AI. I need a privacy policy       and terms of service before I can launch."
AI: 5 relevant specialists found.
User: "Use #2, budget $200."
AI: Creates the task, writes the brief, selects the relevant    project files, attaches them privately to the task, and    invites the specialist. Done.

Community & support

  • Marketplace & signup: stoory.io
  • Issues / bugs: GitHub Issues
  • MCP Registry entry: io.github.StooryBot/stoory-mcp

Are you a specialist?

Stoory MCP recommends specialists from Stoory's marketplace to clients — if you're a developer, designer, lawyer, marketer, or any other freelancer, a free profile makes you eligible to get invited. No commission, ever. Create your free profile at stoory.io/for-specialists.


Disclaimer

Stoory MCP does not replace your AI assistant and does not perform payments or hiring decisions on its own — it prepares the task and hands the decision to you. Stoory does not process payments: client and specialist settle payment for the work directly between themselves, entirely outside Stoory.

來源:README.md,提交 aaa6c67

工具

4

search_specialists

Search specialists

Searches for specialists in the Stoory marketplace via semantic search. Result quality depends mostly on a well-built `query` — see the `query` field description. If a result has <3 hits or only 'Alternative fit', retry with a simpler/broader query (see `query`) instead of asking the user; only after about 3 failed attempts tell the user you have no one to recommend for these requirements and suggest widening the criteria.

輸入參數limitquery必填countrylanguagesgeo_location

create_task

Create task

Invites one or more chosen specialists to a project — does NOT charge payment. budget is a single amount for the whole task (not multiplied per specialist) — whoever accepts it does the work for it. Requires user_confirmed=true, set only after the user has explicitly confirmed in the conversation the choice of specialists, the list of shared files and the estimated cost. Estimate budget yourself from the problem's complexity (e.g. 1h = a single well-localized bug / a simple document fix / a minor graphic tweak; 2h = a standard debug across a few files / a draft legal document (e.g. Privacy Policy) / a landing page design; 3h = an architecture review, a full legal package (ToS+Privacy+GDPR) or a compliance audit, full branding, no clear diagnosis) times the specialist's min_rate_per_hour (from search_specialists) — this field is informational, not enforced, always in USD (the only currency on the marketplace).

輸入參數title必填budget必填language必填timelinedescription必填context_filesspecialist_ids必填user_confirmed必填problem_context必填

get_task

Get task

Returns the whole task record in one call — use it both to check progress and to read the result. Fields: status, title, desc, budget, deadline, timeline, created, modified; specialist_invited and specialist_accepted (arrays of { id, profile_url } — profile_url is already in the right language, show it to the user as a link, not a bare id); and `files` — URLs of every file attached to the task on Stoory (the client's context files plus whatever the specialist delivers). Call it again when the user asks about progress. create_task already returns attached_files for the files it uploaded.

輸入參數task_id必填

cancel_task

Cancel task

Cancels the task, as long as the specialist has not started work yet.

輸入參數task_id必填

版本歷史

1
  1. v0.1.0最新Sep 16, 2026

評分

已滿足適用檢查項的 90%

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

    請在儲存庫或註冊中心條目中宣告授權條款。