DeepWebResearch
MCP-DeepWebResearch provides enhanced web research capabilities for AI assistants, enabling both standard Google searches and parallel multi-query execution for more comprehensive information gathering. Built with TypeScript and Playwright, it features intelligent content extraction that converts web pages to clean markdown, screenshot capture functionality, and a queue management system that handles rate limiting and error recovery. The implementation includes specialized tools for visiting web pages, taking screenshots, and executing batch searches in parallel, making it particularly valuable for workflows requiring deep research across multiple sources or topics.
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/pedrodnt/mcp-deepwebresearch
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve DeepWebResearch 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.