Pagesift MCP Server

by YOLOW92• 181•• Scanned•Claim this listing•Request removal
Web Scraping & Dataai agentsbrowser automationcrawl4ai alternativedata extractiondocument parsing

Rust web scraper & crawler for AI agents: URLs, PDFs and Office files → clean Markdown/JSON. Firecrawl- and Jina Reader-compatible API, MCP server, Python/Node SDKs. Self-hosted single binary.

Pagesift is an open-source mcp server by YOLOW92, written mainly in Rust, with 181 GitHub stars and the AGPL-3.0 license. Its code was last updated Oct 31, 2026.

Scan summary: scanned Nov 5, 2026 at commit 36ec6ec. Seen able to run shell commands, run dynamic code. Scan policy

How to install Pagesift

Built from the start command in the project's README: docker run -d -p 3002:3002 -v pagesift-data:/data -e PAGESIFT_API_KEYS=sk-test ghcr.io/yolow92/pagesift:1.5.2. Check the README for required keys or settings.

Claude Code · Terminal
claude mcp add pagesift -- docker run -d -p 3002:3002 -v pagesift-data:/data -e PAGESIFT_API_KEYS=sk-test ghcr.io/yolow92/pagesift:1.5.2
Claude Desktop · claude_desktop_config.json
{
  "mcpServers": {
    "pagesift": {
      "command": "docker",
      "args": [
        "run",
        "-d",
        "-p",
        "3002:3002",
        "-v",
        "pagesift-data:/data",
        "-e",
        "PAGESIFT_API_KEYS=sk-test",
        "ghcr.io/yolow92/pagesift:1.5.2"
      ]
    }
  }
}
Cursor · .cursor/mcp.json
{
  "mcpServers": {
    "pagesift": {
      "command": "docker",
      "args": [
        "run",
        "-d",
        "-p",
        "3002:3002",
        "-v",
        "pagesift-data:/data",
        "-e",
        "PAGESIFT_API_KEYS=sk-test",
        "ghcr.io/yolow92/pagesift:1.5.2"
      ]
    }
  }
}
VS Code · Terminal
code --add-mcp '{"name":"pagesift","command":"docker","args":["run","-d","-p","3002:3002","-v","pagesift-data:/data","-e","PAGESIFT_API_KEYS=sk-test","ghcr.io/yolow92/pagesift:1.5.2"]}'

What Pagesift can touch

  • Run shell commandsFound in the code by our scan
  • Run dynamic codeFound in the code by our scan
  • Read or write filesNot seen in this scan
  • Read environment and secretsNot seen in this scan
  • Control a web browserLikely, from its own description
  • Connect to databasesNot seen in this scan
  • Read or send messagesNot seen in this scan
  • Touch money or tradingNot seen in this scan
  • Connect to the internetNot run in this scan

"Not seen" means our checks did not find it, and the tool may still do it. Covers commit 36ec6ec, Nov 5, 2026. See the scan policy.

Before you install Pagesift

AgenticMart scanned Pagesift on Nov 5, 2026 with automated checks for hidden code, known-malicious packages, leaked secrets and vulnerable dependencies. The result covers one commit under our scan policy, so review what access you give it and check any advisories shown here.

What it can access

  • An MCP server is a program your AI app starts and talks to. A local one runs with your user's permissions: it can see the files, environment variables and network your account can.
  • Based on its description and topics, it likely needs to control a web browser (visit sites, fill in and submit forms).
  • Based on its description and topics, it likely needs to read and write files on your machine.

Before you install

  1. Run it in a separate browser profile without your logged-in accounts.
  2. Point it at one project folder, never your home directory.
  3. Pin the version you reviewed instead of always installing the latest release.
  4. Read the tool list or scripts before the first run, and keep approval prompts on for actions that write, send or delete.
  • Maintained by YOLOW92 on GitHub, 181 stars and 19 forks. Popularity is not proof of safety.
  • Last code change: Oct 31, 2026.
  • Open-source license: AGPL-3.0.

Pagesift is an open-source mcp server by YOLOW92, written mainly in Rust. Rust web scraper & crawler for AI agents: URLs, PDFs and Office files → clean Markdown/JSON. Firecrawl- and Jina Reader-compatible API, MCP server, Python/Node SDKs. Self-hosted single binary.

At a glance

Stars
181
Forks
19
Language
Rust
License
AGPL-3.0
Created
Oct 2026
Last update
Oct 31, 2026
Type
MCP Server
Price
Free

Topics

ai-agentsbrowser-automationcrawl4ai-alternativedata-extractiondocument-parsingfirecrawlfirecrawl-alternativehtml-to-markdownjina-readerllmmarkdownmcpmcp-serverpdf-extractionragrustself-hostedweb-crawlerweb-scraperweb-scraping

Questions about Pagesift

What is Pagesift?

Rust web scraper & crawler for AI agents: URLs, PDFs and Office files → clean Markdown/JSON. Firecrawl- and Jina Reader-compatible API, MCP server, Python/Node SDKs. Self-hosted single binary.

Who maintains Pagesift?

Pagesift is maintained by YOLOW92 on GitHub (YOLOW92/pagesift). AgenticMart lists it from public repository data.

Is Pagesift safe to use?

AgenticMart scanned Pagesift on Nov 5, 2026 with automated checks for hidden code, known-malicious packages, leaked secrets and vulnerable dependencies. The result covers one commit under our scan policy, so review what access you give it and check any advisories shown here.

What license does Pagesift use?

It is published under the AGPL-3.0 license.

Pagesift alternatives

View more →

Similar mcp servers in Web Scraping & Data, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.

NameStarsLicenceLast updatedScan
Pagesift (this page)
YOLOW92
181AGPL-3.0Oct 31, 2026Scanned, no flagged issues
Scrapling
D4Vinci
91kBSD-3-ClauseOct 31, 2026Scanned, no flagged issues
Apify MCP Server
apify
14kMITOct 31, 2026Scanned, no flagged issues
Firecrawl MCP Server
firecrawl
7.7kMITOct 29, 2026Scanned, no flagged issues
Unstract
Zipstack
7.4kAGPL-3.0Oct 30, 2026Scanned, no flagged issues
Exa MCP Server
exa-labs
5.2kMITOct 30, 2026Scanned, no flagged issues