Web Fetcher
Fetcher MCP is a server that enables AI assistants to retrieve web page content using Playwright's headless browser capabilities. It excels at handling dynamic JavaScript-heavy websites by executing client-side code, and includes intelligent content extraction through Mozilla's Readability algorithm to remove ads and non-essential elements. The implementation offers both single URL and batch fetching tools, supports HTML or Markdown output formats, and automatically blocks unnecessary resources like images and stylesheets to improve performance. This tool is particularly valuable for research workflows, content analysis, and information gathering that requires processing of modern web applications.
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
- browser-automation
- Source
- PulseMCP
- Repository
- github.com/jae-jae/fetcher-mcp
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve Web Fetcher 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.