# GuDaStudio/GrokSearch

Integrate Grok's powerful real-time search capabilities into Claude via the MCP protocol!

Repository: https://github.com/GuDaStudio/GrokSearch
Canonical: https://ross.abutalabs.com/products/groksearch
Homepage: https://code.guda.studio
Language: Python
License: MIT
License Family: permissive
Last push: 2026-03-09T03:22:47+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 71, release rhythm 35, longevity 20
- inputs: {"age_days": 286, "days_push": 177, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1849, forks 193 (observed 2026-08-28T04:05:44.124196+00:00)

## What it is
GrokSearch is an MCP server built on FastMCP that gives Claude Code and other LLM clients real-time web access via a dual-engine architecture: Grok for AI-powered search and Tavily (with Firecrawl fallback) for web fetching and site mapping. It is configured as a stdio MCP tool and can override Claude Code's built-in WebSearch/WebFetch.

## Use cases
- give claude real-time web search via mcp
- reduce llm hallucinations by fetching up-to-date docs
- scrape and extract web page content for an ai agent
- map a website's structure for an llm client
- route claude code web searches through grok
- add web access to cherry studio or other mcp clients

## When to choose
- you use Claude Code or another MCP-compatible client and need live web search
- you want AI-driven search plus high-fidelity page extraction with automatic fallback
- you want to disable built-in web tools and force routing through a better search backend

## When to avoid
- you don't have a Grok (OpenAI-compatible) API key
- you need a hosted search service rather than a locally run MCP server
- your client doesn't support the MCP protocol

## Facets
- artifact type: service
- maturity: active
- function: mcp, search-engine, web-scraping, agent-framework, http-client
- domain: large-language-models, developer-tools
- platform: python, cli, cross-platform
- tags: mcp-server, grok, tavily, claude-code, fastmcp, web-search, firecrawl, llm-tools, ai-agents, search, retrieval-augmented-generation, docker

## Member repositories
- GuDaStudio/GrokSearch (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:44.124196+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:17:15.992111+00:00, confidence not recorded.
  - readme: https://github.com/GuDaStudio/GrokSearch (fetched 2026-08-28T04:05:44.124196+00:00, sha ba1d873f8e6e)
  - homepage: https://code.guda.studio (fetched 2026-08-29T10:56:33.313625+00:00, sha 8dc0b86ec1b6)
- Data as of 2026-08-30T08:39:29.467469+00:00.