Google Search
G-Search MCP is a powerful server for performing parallel Google searches with multiple keywords simultaneously, using Playwright to automate browser interactions. Developed by jae-jae, it features intelligent CAPTCHA detection with automatic switching to visible browser mode when verification is needed, browser state persistence to reduce detection likelihood, and user behavior simulation to mimic real browsing patterns. The implementation includes robust error handling, configurable search parameters (result limits, timeouts, locales), and returns structured JSON results, making it ideal for applications requiring efficient batch searching or when AI assistants need direct access to search engine results without triggering anti-bot measures.
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/jae-jae/g-search-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Google Search 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.