Pagesift MCP Server
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 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{
"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"
]
}
}
}{
"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"
]
}
}
}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
- Seen in this scan, either in the code or while it ran.Run shell commandsFound in the code by our scan
- Seen in this scan, either in the code or while it ran.Run dynamic codeFound in the code by our scan
- Our checks did not find this. The tool may still do it.Read or write filesNot seen in this scan
- Our checks did not find this. The tool may still do it.Read environment and secretsNot seen in this scan
- Not checked directly. Its own description suggests it does this.Control a web browserLikely, from its own description
- Our checks did not find this. The tool may still do it.Connect to databasesNot seen in this scan
- Our checks did not find this. The tool may still do it.Read or send messagesNot seen in this scan
- Our checks did not find this. The tool may still do it.Touch money or tradingNot seen in this scan
- Our checks did not find this. The tool may still do it.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
- Run it in a separate browser profile without your logged-in accounts.
- Point it at one project folder, never your home directory.
- Pin the version you reviewed instead of always installing the latest release.
- 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
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.
| Name | Stars | Licence | Last updated | Scan |
|---|---|---|---|---|
| Pagesift (this page) YOLOW92 | 181 | AGPL-3.0 | Oct 31, 2026 | Scanned, no flagged issues |
| Scrapling D4Vinci | 91k | BSD-3-Clause | Oct 31, 2026 | Scanned, no flagged issues |
| Apify MCP Server apify | 14k | MIT | Oct 31, 2026 | Scanned, no flagged issues |
| Firecrawl MCP Server firecrawl | 7.7k | MIT | Oct 29, 2026 | Scanned, no flagged issues |
| Unstract Zipstack | 7.4k | AGPL-3.0 | Oct 30, 2026 | Scanned, no flagged issues |
| Exa MCP Server exa-labs | 5.2k | MIT | Oct 30, 2026 | Scanned, no flagged issues |