Web Fetch
Fetch MCP Server provides web content retrieval capabilities through four specialized tools: fetch_html, fetch_json, fetch_txt, and fetch_markdown. Built by Zach Caceres, this TypeScript implementation uses modern fetch API with customizable headers, JSDOM for HTML parsing, and TurndownService for Markdown conversion. The server runs on stdio transport, making it easy to integrate with desktop applications that support the Model Context Protocol. It's particularly useful for workflows requiring web scraping, content analysis, or data extraction in various formats without leaving the conversation interface.
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 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- api-integration
- Source
- PulseMCP
- Repository
- github.com/tokenizin/mcp-npx-fetch
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
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.