Web Research
MCP-WebResearch provides AI assistants with web browsing capabilities for conducting research through Google searches and webpage content extraction. Built with TypeScript using Playwright for browser automation and Turndown for HTML-to-Markdown conversion, it offers tools to search Google, visit webpages, and capture screenshots while handling common challenges like consent dialogs and bot detection. The implementation includes an agentic research prompt that guides assistants through iterative research workflows, making it particularly valuable for deep topic exploration, fact-checking, and information gathering directly within AI conversations.
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 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · 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/chuanmingliu/mcp-webresearch
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Web Research 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.