pulsemcp verified Safe content atomic mcp-remote

Gemini DeepSearch

This MCP server provides automated multi-step web research capabilities using Google Gemini models and Google Search API to perform deep information gathering with citation tracking. Built by Alex Cong using Python with LangGraph workflow orchestration, FastMCP integration, and Google's generative AI tools, it implements a sophisticated research agent that generates diverse search queries, conducts parallel web searches, reflects on knowledge gaps through iterative loops, and synthesizes final answers with proper source attribution. The implementation offers configurable effort levels (low/medium/high) that control research depth through query count and loop iterations, supports both HTTP API and stdio MCP deployment modes, and includes LangGraph Studio integration for workflow visualization, making it valuable for research tasks requiring comprehensive information synthesis, fact-checking with source verification, and scenarios where AI assistants need to gather current information beyond their training data through systematic web exploration.

Cognium trust score

100%

Tier

Verified

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: devops-ci
Source: PulseMCP
Repository: github.com/alexcong/gemini-deepsearch-mcp
Author type: human
Last scanned: 2026-09-19
Updated: 2026-09-19

View source Find related skills

MCP

Resolve Gemini DeepSearch 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

Swap --scope user for --scope project to commit it to .mcp.json.

Your client Same endpoint everywhere; only the config key differs. The full list is in the descriptor.

Claude Desktop · Settings → Connectors → Add custom connector

https://api.skillsregistry.net/mcp

Paste the URL as the connector endpoint. No authentication.

ChatGPT · Settings → Connectors → Create (developer mode) → MCP server URL

https://api.skillsregistry.net/mcp

Authentication: none. Works in chat and deep research — the server exposes the connector search and fetch tools.

Codex CLI · ~/.codex/config.toml

[mcp_servers.skillsregistry]
url = "https://api.skillsregistry.net/mcp"