Provides meta-search capabilities via SearXNG, enabling web searches with academic bias, deduplication, and access to raw JSON results including answers and infoboxes.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@carbs Deep research on the effects of intermittent fasting on metabolism"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A research MCP server that bundles SearXNG (meta-search) + Crawl4AI (JS-rendered web scraping) behind one command. Runs 100% local.
make up # generates .env (token) if needed, starts searxng + crawl4ai + carbsMCP endpoint: http://localhost:8765/mcp (streamable-http).
Register in your agent (opencode example):
// ~/.config/opencode/opencode.jsonc
"mcp": {
"carbs": {
"type": "http",
"url": "http://127.0.0.1:8765/mcp",
"enabled": true
}
}For Claude Code / Codex, the same http://127.0.0.1:8765/mcp URL works in
their MCP configs.
Related MCP server: searxNcrawl
Tool | Purpose |
| Meta-search with academic bias, deduped |
| Raw SearXNG JSON (answers, infoboxes) |
| Single URL → clean markdown (with fallback chain) |
| Batch crawl, concurrency-capped |
| LLM JSON extraction from a page |
| Search → parallel scrape → synthesize |
| Backend status |
Everything is env-driven — see src/carbs/config.py for the full list
(SEARXNG_URL, CRAWL4AI_URL, CRAWL4AI_API_TOKEN, LLM_PROVIDER, cache
TTL, crawl concurrency, ports).
uv sync --dev
uv run pytest
uv run python -m carbs --http --host 127.0.0.1 --port 8765 # run MCP locally against running backendsMIT
This server cannot be deployed
MCP server for Firecrawl — web search, scraping, and biomedical/arXiv paper search.
An MCP server for deep research or task groups
Free web search for AI agents. No API key required. Hosted MCP in active development.
