Webclaw
Webclaw is a Rust-based web extraction engine that impersonates Chrome at the TLS level, allowing it to bypass bot-detection systems that block standard fetch requests. It exposes 10 tools — scrape, crawl, search, extract, summarize, brand, diff, map, batch, and research — as an MCP server for use with Claude, Cursor, Windsurf, and other compatible clients. Output is clean markdown optimized for language models, reducing token usage by approximately 67% compared to raw HTML. Eight tools work locally without an API key; the hosted service at webclaw.io adds cloud-based JavaScript rendering and proxy rotation with free and paid tiers.
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
- browser-automation
- Source
- PulseMCP
- Repository
- github.com/0xmassi/webclaw
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Webclaw 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.