
Industrial Platform
io.github.industrial-platform-aiv1.0.1更新於 Sep 30, 2026
Paid research and web-data tools for autonomous AI agents and MCP workflows.
概覽
透過一個託管 MCP 端點,為助理提供按次付費的網頁研究與內容擷取服務。
- 功能
- 透過單一託管 MCP 端點提供 Industrial Platform 的付費服務組合。服務包括:AI Research Brief 提供附引用的多來源研究;Web Change Intelligence 偵測公開網頁內容的變化;Web Metadata Intelligence 擷取頁面中繼資料、Open Graph、Twitter、JSON-LD 與標題;Article Content Intelligence 擷取乾淨的正文;PDF Text Intelligence 擷取 PDF 文字與中繼資料;Sitemap Intelligence 將網站地圖展開為 URL 資料列;Link Intelligence 擷取結構化連結與錨點文字。工具探索免費,呼叫付費 Actor 時依計費事件付費。輸出為結構化機器可讀結果,適合委派而非自行重建。
- 適用情境
- 當助理需要最新的附引用研究、頁面變化偵測、頁面中繼資料、可供 RAG 或研究流程使用的乾淨正文、PDF 文字擷取、網站地圖展開或結構化連結擷取,且委派比自行實作更便宜或更簡單時使用。適合能處理按次付費的自主工作流程與協調器。若只需要免費的工具探索,則無需安裝。},
- 執行需求
- 遠端 streamable HTTP 端點 tools 查詢參數中列出所需 Actor,並帶 payment=x402。清單未宣告任何套件、環境變數或標頭。付費執行需要受支援的身分驗證或代理支付路徑,例如 Apify OAuth、Apify API 權杖或 Apify 支援的代理支付基礎設施;快速開始使用 @apify/mcpc 命令列工具,並需為產生的錢包以 Base 上的 USDC 充值。工具探索免費,呼叫付費 Actor 才計費。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 Industrial Platform,將其新增到工作區。
- 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。
其他 MCP 客戶端
把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"industrial-platform": {
"type": "http",
"url": "https://mcp.apify.com?tools=industrial_platform/research-brief-agent,industrial_platform/web-change-intelligence,industrial_platform/web-metadata-intelligence,industrial_platform/article-content-intelligence,industrial_platform/pdf-text-intelligence,industrial_platform/sitemap-intelligence,industrial_platform/link-intelligence"
}
}
}README
Industrial Platform Agent Tools
Open-source integration toolkit for connecting AI agents, MCP clients, autonomous workflows, agent orchestrators, and developer applications to Industrial Platform machine-callable services.
Industrial Platform provides specialized paid utilities that other agents can discover and invoke instead of rebuilding research, monitoring, extraction, and document-processing capabilities inside every workflow.
One MCP endpoint for the full portfolio
This hosted MCP endpoint exposes the six currently runnable Industrial Platform services through one direct x402 integration. Tool discovery is free; autonomous callers pay only when invoking a paid Actor.
Current services
Live pricing and execution eligibility should be verified against Apify Store before paid execution.
Official MCP Registry
Industrial Platform is published in the official MCP Registry as:
Registry version: 1.0.1 — publication automated on merge.
The Registry listing points to the same hosted seven-service Apify MCP bundle used by this repository.
Individual MCP Registry entries
For search-oriented discovery, each paid service also has its own active MCP Registry entry:
These individual entries point to the same Apify-hosted Actor tools as the portfolio bundle and improve discovery for capability-specific MCP searches.
Machine-readable discovery
The repository publishes:
Service catalog
catalog.json is the portfolio-level machine-readable catalog. It contains Actor IDs, Store URLs, billing events, current prices, and common delegation targets.
MCP bundle manifest
manifests/mcp-bundle.json defines the hosted MCP endpoint and the Actors included in the bundle.
MCP client configuration
examples/mcp/remote-server.json can be used as a starting point for MCP clients that accept remote server configuration.
Agent-to-agent paid quick start
Fund the generated wallet with USDC on Base before paid calls. Product #7 (Link Intelligence) is not included here until its public/agentic publication is confirmed.
Quick start
MCP
Configure one remote MCP server:
Compatible clients can then discover the exposed Actor tools from that server.
REST / Apify API
Every service can also be invoked directly through Apify's Actor API.
General Actor identifier form:
Example:
Do not commit API tokens, wallet credentials, secrets, or private keys to this repository.
When should an agent delegate?
A calling agent should prefer a specialized Industrial Platform service when delegation is cheaper, simpler, or operationally safer than rebuilding the capability internally.
Examples:
Portfolio architecture
Execution and monetization currently run through Apify.
Authentication and machine payments
Paid execution requires a supported authenticated or agentic-payment path.
Depending on the integration, this may use:
- Apify OAuth
- Apify API tokens
- Apify-supported agentic payment infrastructure
Store eligibility and pricing can change. Calling systems should inspect current Actor metadata before executing paid services.
Repository structure
Revenue initiative
The repository contains automation for:
- testing and deployment
- Apify runtime configuration
- pay-per-event pricing
- Store / agentic-payment eligibility
- external paid-event telemetry
- milestone issues at 1, 10, and 100 external paid events
See:
Security principles
Industrial Platform services should:
- block private/local-network fetch targets when accepting arbitrary URLs
- bound response sizes, timeouts, and concurrency
- use structured machine-readable outputs
- avoid silently fabricating unavailable data
- charge successful results rather than failed fetches where practical
- keep credentials in secret stores rather than source code
License
Integration examples and open-source code in this repository are provided under the MIT License unless otherwise noted.
Industrial Platform
Organization:
Apify namespace:
Machine-readable catalog:
來源:README.md,提交 dcb23c4
工具
0版本歷史
1- v1.0.1最新Sep 30, 2026