Web Fetch
Web content fetching MCP server built by kwp-lab that retrieves and processes web pages into markdown format with automatic image extraction and proxy support. Forked from @smithery/mcp-fetch, this implementation replaces node-fetch with node-fetch-native to enable HTTP/HTTPS proxy routing through environment variables (http_proxy, https_proxy) or custom MCP_HTTP_PROXY configuration. The server uses Mozilla Readability for content extraction, JSDOM for HTML parsing, and Turndown for markdown conversion, automatically identifying and listing image URLs found within article content, making it valuable for AI assistants that need to access web content through corporate proxies or restricted network environments while maintaining clean markdown output with embedded media references.
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
- media
- Source
- PulseMCP
- Repository
- github.com/kwp-lab/mcp-fetch
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve Web Fetch 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.