Deep Research Gemini
This MCP server provides AI assistants with deep web research capabilities through a multi-agent system built using CrewAI and powered by Google's Gemini 2.5 Pro, with LinkUp API integration for comprehensive web searches. The implementation orchestrates two specialized agents - a web searcher that conducts up to 5 strategic searches covering different aspects of a topic, and a research writer that synthesizes findings into detailed 1500-2000 word reports with proper structure and citations. Built with intelligent search depth selection (alternating between standard and deep searches), global search limiting, retry mechanisms for API rate limiting, and enhanced timeout handling, it serves researchers needing thorough multi-angle investigations, content creators requiring well-sourced analytical reports, and teams wanting AI-powered research automation that goes beyond simple search queries to deliver publication-ready analysis.
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
- search
- Source
- PulseMCP
- Repository
- github.com/ragha02/deep_rsrch_gemini
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Deep Research Gemini 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.