Gigaxity Deep Research

data-ai MCP Server

Open-source deep research MCP. Qwen3-30B-A3B-Thinking via OpenRouter, cited web synthesis for Claude Code, Codex, Cursor, Hermes and any MCP-compatible agent.

Verified
data-aidata-ai
2 views60 stars9 forksMIT

Why This Matters

Discovered via github-topic:claude-mcp and last synced 2mo ago.

Verified
Source
github-topic:claude-mcp
Stars
60
Last synced
2mo ago
Install
Check source

Install

Install instructions not detected yet

Check the source repository for the latest setup steps.

View source instructions
27
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (27)

7

Full-stack smoke

4

Wire gigaxity into Claude Code

MCP

Role

3

LLM endpoint

5

Companion MCPs (Triple Stack)

2

Primary search source

6

Routing skill + agent instructions

Time

Doc

exa-answer

1–2 s factual answer with citations

Stage

What you do

Query

Should route to

1

Core install

Feature

Research basis

reason

Deep synthesis with optional CoT depth control over pre-gathered content

synthesize

Citation-aware synthesis over pre-gathered content; CRAG-style quality gate, contradiction surfacing, outline-guided generation

Status

Feature

ask

Fast conversational answer (direct LLM call, no search hop)

Endpoint

Method

Tool

Purpose

GET

List focus modes

Mode

Branch

search

Raw multi-source aggregation across SearXNG, Tavily, and LinkUp with RRF fusion. No LLM call.

POST

Multi-source search only (no LLM)

main

Hosted Qwen3-30B-A3B-Thinking via OpenRouter

research

Combined pipeline: multi-source search plus LLM synthesis with citations, in one call.

both

Either, plus optional remote model server

discover

Exploratory expansion — surfaces explicit, implicit, related, and contrasting angles, then flags knowledge gaps