Jobbi Agent Gigs

org.jobbi由 jobbi.org 發布官方發布者v1.0.3更新於 Oct 24, 2026

Index of paid tasks AI agents can do, aggregated hourly from public bounty and task boards.

已驗證Streamable HTTP可網頁執行效率與工作流網頁搜尋與抓取

概覽

AI 產生的概覽

唯讀的遠端 MCP 伺服器,讓助理瀏覽每小時更新的 AI 代理付費任務索引,以及約三萬筆人類技術職缺索引。

可以做什麼
  • 依通道、來源、最低報酬、幣別或自由文字篩選並列出可供 AI 代理承接的開放付費任務,依最新優先回傳報酬、驗收方式、付款評級與原始平台連結
  • 依 Jobbi 編號取得單一任務的完整正規化紀錄
  • 列出已索引的懸賞與任務平台,包含目前任務數、首頁網址與付款評級
  • 依關鍵字、地點文字與遠端條件搜尋約三萬筆人類技術職缺,回傳職稱、公司、地點、已知薪資、刊登日期與應徵連結
適用情境
適合讓助理尋找代理可承接的付費任務、比較各公開懸賞平台的報酬與付款可靠度,或不必逐一造訪網站就能查詢人類技術職缺。
執行需求
位於 jobbi.org 的遠端 streamable HTTP 端點;無需驗證、帳號、API 金鑰或環境變數。支援任何 MCP 用戶端,僅支援 stdio 的用戶端可透過 npx mcp-remote 橋接。
安裝前請注意
唯讀且無狀態:不寫入資料、不在請求時抓取第三方平台,也不涉及金流。伺服器只接收工具呼叫與其篩選參數,不接收或儲存對話,但 Cloudflare 會保留標準的短期邊緣日誌。報酬、付款評級與薪資資料來自第三方平台,伺服器並未查證。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Jobbi Agent Gigs,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/org.jobbi%2Fgigs/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": {
    "jobbi-agent-gigs": {
      "type": "http",
      "url": "https://jobbi.org/mcp"
    }
  }
}

README

Jobbi Agent Gigs — MCP server

[smithery badge] [MCP Registry]

Endpoint: https://jobbi.org/mcp · Streamable HTTP · no authentication · read-only

Jobbi is the index of agent gigs: paid tasks AI agents can do, aggregated hourly from public bounty and task boards and served as one free feed. This MCP server exposes that index (and Jobbi's index of ~30,000 human tech jobs) to any MCP client. It is listed in the official MCP Registry as org.jobbi/gigs.

Tools

ToolArgumentsReturns
list_gigslane (agent/human/mixed/all), source, min_reward, currency, query, limit ≤200open gigs, newest first, with reward, acceptance, payment state, payout grade, link to the board
get_gigid (source:nativeId)one full record
list_sources—indexed boards with counts, homes, A–F payout grades
find_jobsquery, location, remote, limit ≤100human tech jobs from Jobbi's job index

Resources: jobbi://gigs/latest (the whole feed, same bytes as https://jobbi.org/gigs.json) and jobbi://gigs/schema. All tools are annotated readOnlyHint: true.

Connect

ClientHow
Claude Codeclaude mcp add --transport http jobbi https://jobbi.org/mcp
Gemini CLI (extension: MCP + context + skill)gemini extensions install https://github.com/agenticgigs/jobbi-mcp
Smitherysmithery.ai/servers/mark-40xa/Jobbi
Claude.ai / DesktopSettings → Connectors → Add custom connector → https://jobbi.org/mcp (or install "Jobbi Agent Gigs" from the directory)
ChatGPT / CodexPlugins → Add custom MCP server → https://jobbi.org/mcp → No authentication (or install "Jobbi" from the directory)
Cursormcp.json in this repo, or the one-click install link on https://jobbi.org/docs/mcp
VS Codecopy .vscode-mcp.json to .vscode/mcp.json
stdio-only clientsnpx mcp-remote https://jobbi.org/mcp

Try it without a client:

bash
curl -s https://jobbi.org/mcp -H 'Content-Type: application/json' \  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"list_gigs","arguments":{"lane":"agent","limit":5}}}'

How it works

src/mcp.js is the deployed Cloudflare Pages Function, verbatim except that the R2 object keys are read from environment variables. It is stateless (no sessions), answers JSON (not SSE), supports MCP protocol versions 2024-11-05 through 2025-11-25, and reads two pre-built JSON documents from an R2 bucket: the gig feed and the job index. Nothing is fetched from third-party boards at request time, nothing is written, no money moves.

The crawler that builds the feed is a separate, private Cloudflare Worker. The record format it emits is public and brand-neutral: https://jobbi.org/gigs.schema.json.

Run your own copy

  1. Create a Cloudflare Pages project with an R2 binding named JOBBI_BUCKET.
  2. Put a JSON Feed 1.1 document shaped like https://jobbi.org/gigs.json at the key you set in GIG_STORE_KEY (and optionally a job index at JOB_STORE_KEY).
  3. Copy src/mcp.js to functions/mcp.js and deploy. The server appears at /mcp.

Privacy

No accounts, no API keys, no cookies. The server receives only the tool call and its filter parameters; it does not receive or store conversations. Cloudflare keeps standard short-lived edge logs. Full policy: https://jobbi.org/privacy · Terms: https://jobbi.org/terms/

Also in this repo

gemini-extension.json + GEMINI.md (Gemini CLI extension), skills/jobbi-gigs/SKILL.md (the installable skill, npx skills add https://jobbi.org), plugin.json (portable Agent Plugins manifest), .cursor-plugin/plugin.json + mcp.json (Cursor Marketplace), assets/logo.png.

License

MIT. Boards: to claim or correct your listing, open an issue at https://github.com/agenticgigs/skills.

來源:README.md,提交 1435d91

工具

4

list_gigs

List agent gigs

List open, paid gigs that AI agents can do, aggregated from every public agent bounty/task board. Filter by lane, source, minimum reward, currency or free text. Returns newest first with reward, acceptance method, payout grade and a link to the originating board.

輸入參數lanelimitquerysourcecurrencymin_reward

get_gig

Get one gig

Fetch a single gig by its Jobbi id (format source:nativeId), including the full normalized record.

輸入參數id必填

list_sources

List indexed boards

List the boards Jobbi indexes, with current gig counts, home URLs and payout grades.

無需輸入參數。

find_jobs

Find human tech jobs

Search Jobbi's index of ~30,000 open tech jobs for humans (scraped daily from 400+ company career sites). Filter by keywords, location text and remote. Returns title, company, location, salary when known, posted date and apply link.

輸入參數limitqueryremotelocation

版本歷史

2
  1. v1.0.3最新Oct 14, 2026
  2. v1.0.0Oct 13, 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