DataFetch
DataFetch is a secure web content fetching server that provides sandboxed access to web pages without JavaScript execution, featuring comprehensive security protections including URL validation, path traversal prevention, prompt injection detection, and automatic cookie banner removal. The implementation uses aiohttp for HTTP operations with proper cookie handling, BeautifulSoup for HTML parsing and sanitization, and operates within a configurable sandboxed working directory to prevent file system access outside designated areas. It exposes five core tools for fetching webpages in multiple formats (markdown, text, HTML), extracting and categorizing links, safely downloading files with size limits, retrieving structured metadata including Open Graph and Twitter Cards, and checking URL status.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-02.
Scan details: Circle-IR · 2026-09-02 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- social-media
- Source
- PulseMCP
- Repository
- github.com/undici77/mcpdatafetchserver
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve DataFetch from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.