Brave Deep Research
Brave Deep Research MCP Server combines the Brave Search API with Puppeteer-powered web scraping to provide AI assistants with comprehensive research capabilities. Unlike standard search tools that only return snippets, this implementation visits web pages to extract full content and can traverse links at configurable depths (up to 3 levels). Developed by suthio, it intelligently identifies and extracts main content from pages while filtering out navigation elements, ads, and footers. The server exposes a single deep-search tool that accepts query parameters for search terms, result count, and exploration depth, making it particularly valuable for in-depth research requiring detailed information beyond what search snippets provide.
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/suthio/brave-deep-research-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Brave Deep 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.