Serper Search
Serper Search MCP is a server implementation that provides AI assistants with powerful web search capabilities through the Serper API. It features two main tools: a standard Google search tool for quick information retrieval and a Deep Research tool that breaks complex queries into focused sub-queries, gathers information from multiple sources, and synthesizes findings into comprehensive responses with citations. Built with TypeScript and following domain-driven design principles, it includes configurable research depth levels, telemetry for quality improvement, and integration with OpenRouter for LLM-powered research orchestration. This implementation is particularly valuable for users who need thorough, well-cited research on complex topics without leaving their AI assistant interface.
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
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/nighttrek/serper-search-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Serper 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.