Research Multi-API Search
ResearchMCP is a web search tool that combines multiple search APIs (Brave Search, Tavily Search, and Wikipedia) to provide comprehensive research capabilities through the MCP protocol. Built with Deno and Hono, it uses a hexagonal architecture with domain-driven design principles to intelligently route queries to the most appropriate search providers based on query classification. The implementation features automatic query categorization, parallel search execution, result deduplication, and caching to improve performance. It's particularly valuable for AI assistants that need to search the web for current information without requiring users to implement complex API interactions themselves.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- search
- Source
- PulseMCP
- Repository
- github.com/riii111/researchmcp
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve Research Multi-API 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.