DeepSFetch

io.github.ermultimidiaPublished by GitHub account ermultimidiav2.0.1Updated Nov 2, 2026

Web scraping, extraction and search for AI agents. Hosted MCP with workspace API keys.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

Hosted MCP endpoint that lets an assistant scrape, extract and search web content for AI agents and automation, billed in workspace credits.

What you can do
  • Submit web collection jobs for pages and listings, with HTTP-only or browser fallback configurations.
  • Poll and resume collection jobs, and estimate credit cost before running one.
  • Extract structured fields such as names, prices and currencies from HTML, JSON-LD or CSS selectors.
  • Produce clean documentation chunks with source metadata and content hashes for RAG and vector stores.
  • Search the web and retrieve content for agent and automation pipelines.
When to use it
Use it when an assistant needs to gather web pages or listing data, monitor prices, or feed clean documentation into RAG pipelines without running its own scraping or browser infrastructure.
Requirements
A remote MCP endpoint reached over streamable HTTP, authenticated with a bearer token in the Authorization header carrying a DeepSFetch workspace API key. A DeepSFetch account is needed, and collection consumes workspace credits.
Before you install
Collection consumes paid workspace credits, so set explicit credit caps and check estimates first. The API key is a workspace credential sent in the Authorization header. Submitted pages and extracted data go to the hosted DeepSFetch service, and collection jobs write results into your workspace.

Installation

In SourceWeft

  1. Open DeepSFetch in the dashboard and add it to a workspace.
  2. Connect Authorization token credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.ermultimidia%2Fdeepsfetch/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "deepsfetch": {
      "type": "http",
      "url": "https://mcp.deepsfetch.com/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

English | Português

DeepSFetch Developer Kit

⭐ If these n8n workflows, SDKs, or MCP tools save you time, please give this repository a Star on GitHub! It helps other automation builders discover the toolkit.

[DeepSFetch n8n Workflow — Automated Collection & Price Monitoring]

Complete manual: 33 step-by-step guides — API, MCP, SDKs, CLI, collections, monitors, files, integrations and billing.

Collect web content for AI agents and automation with explicit credit limits.

Open-source JavaScript and Python clients, a CLI, and n8n integration code for the hosted DeepSFetch API. Start with one public HTML page, inspect the result, and build from there.

This repository contains client-side tools. The collection engine and hosted service are not included. Running the examples requires a DeepSFetch account and API key; collection consumes workspace credits. See current plans.

Ready-to-use n8n Workflows & Community Node

Automate structured HTML extraction in n8n with explicit credit caps, idempotency keys, and field validation before sending data to your alerts, spreadsheets, or AI/RAG pipelines.

Ready TemplateUse CaseWhat It Extracts & DeliversSetup & Download
Price MonitoringTrack product price changes on a scheduleValidated name, price, and currency (JSON-LD / CSS) with baseline comparisonConfigure & Download JSON · n8n Guide
Product CatalogExtract up to 100 items from a listing pageStructured item arrays with per-item field validation (no pagination)Configure & Download JSON · n8n Guide
AI / RAG DocumentationFeed clean documentation into vector stores or LLMsSource metadata, stable document IDs, content hash (change detection), and chunksConfigure & Download JSON · n8n Guide

Install the n8n Community Node (n8n-nodes-deepsfetch)

For self-hosted n8n, install via the UI (Settings → Community Nodes → Install → n8n-nodes-deepsfetch) or manually in your community nodes folder:

sh
npm install n8n-nodes-deepsfetch

(Using n8n Cloud? You can download the standard HTTP Request workflow templates directly from Guided Setup without installing a community node.)

📸 View n8n Node Configuration & Validated JSON Output Screenshots

1. Starting a Collection (Start Collection operation with payload & language selection): [DeepSFetch Start Collection Node in n8n]

2. Validated Output & Price Comparison (Compare price step with structured JSON result): [DeepSFetch Price Comparison Output in n8n]

Get your first result

Requires Node.js 22+. Create a key in API keys. From the repository root, set it for the current terminal session and run the dependency-free example:

PowerShell:

powershell
$env:DEEPSFETCH_API_KEY = 'YOUR_DEEPSFETCH_API_KEY'node examples/scrape.mjs https://example.com

macOS / Linux:

sh
export DEEPSFETCH_API_KEY='YOUR_DEEPSFETCH_API_KEY'node examples/scrape.mjs https://example.com

The example submits one HTTP-only collection with a maximum of 3 DeepSFetch credits and browser fallback disabled, then polls the same job. It prints the completed job as JSON. This cap is not a promise of a free or successful collection. JavaScript-dependent pages need another configuration. See getting started for failure handling and resuming a job.

Choose your integration

ToolInstall or guideWhat is included
JavaScript SDKnpm install @deepsfetch/sdkAPI v2 client and job polling
CLInpm install -g @deepsfetch/cliCommands for collection, jobs and estimates
Python SDKpython -m pip install ./packages/deepsfetch-sdk-pythonSource installation; PyPI release pending
MCPRemote connection guideConfiguration for the hosted MCP endpoint
n8nnpm install n8n-nodes-deepsfetch · GuideSource for the npm-published community node

The remote MCP server implementation is not included here. The n8n node is not verified by n8n. The remote MCP is listed in the official registry. Native partnerships and a self-hosted collection engine are not claimed by this repository.

CLI quickstart

After installing the CLI and setting the environment variable above:

sh
deepsfetch scrape --file examples/scrape-request.json --wait

The CLI writes its idempotency key to stderr. If a submission's outcome is unknown, retry the same request with --idempotency-key THE_SAME_KEY. Once you have a job ID, use deepsfetch job JOB_ID --wait instead of submitting another collection.

Open tools and hosted service

CapabilityIn this repositoryHosted DeepSFetch
JavaScript SDK, Python SDK, CLISource and testsConnect to API v2
n8n community nodeSource distributed as JavaScriptCalls collection integration endpoints
MCPConnection guideRemote server
Collection engine, browser infrastructureNot includedManaged by DeepSFetch
Accounts, credits, billing and dashboardNot includedManaged by DeepSFetch

Develop locally

sh
npm install --ignore-scripts
npm test
npm run check

Run Python tests from the repository root:

sh
python -m pip install ./packages/deepsfetch-sdk-python
python -m unittest discover -s packages/deepsfetch-sdk-python/tests

Tests use fixtures and a local HTTP server; they do not submit paid collections. See contributing, security, and the roadmap.

Resources

MIT license applies to the tools in this repository. Using the hosted service is subject to its own terms and credit limits.

Try it and share feedback

Read the first-collection tutorial, run the operational smoke test, and share your first-run experience.

The authenticated Firecrawl comparison includes results, limitations and reproducible code. The published DEV tutorial walks through signup, first collection and MCP. Also see the Smithery listing, with instructions and limits in the MCP guide.

Source: README.md at commit 3b22714

Tools

0
This server asks for a credential such as an API key, so SourceWeft could not read its tools without one and has not indexed them.

Version history

1
  1. v2.0.1LatestOct 11, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.