Provides meta-search capabilities via SearXNG, enabling web searches with academic bias, deduplication, and access to raw JSON results including answers and infoboxes.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
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
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
One MCP server for all web data. Scrape, search, crawl, and AI research in one install.
Web search API and MCP server for developers building AI agents.
Unified 15-tool SEO, SERP, clean Markdown & GEO (LLM citation Share-of-Voice) MCP server.
