Fetch
MCP Fetch is a server that enables Claude Desktop and other MCP clients to retrieve and process web content. Built by kazuph, it fetches URLs, extracts content as markdown, and handles images intelligently - automatically processing them for optimal viewing (merging vertically with size limits) and preparing them for clipboard operations. The implementation uses Node.js with libraries like Sharp for image processing, JSDOM and Readability for content extraction, and includes features like robots.txt compliance and animated GIF handling. Particularly useful for research workflows where users need to bring external web content into their AI conversations without manual copying and formatting.
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
- media
- Source
- PulseMCP
- Repository
- github.com/jeremynixon/mcp-fetch
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve 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.