Searxng Deepdive
Wraps SearXNG's meta-search API with four distinct tools: broad search across all engines, targeted search on specific engines like arxiv or pubmed, category-scoped search, and a lightweight HTML-to-Markdown URL reader with TOC extraction. The server dynamically injects your instance's actual engine and category lists into tool descriptions so the LLM knows what's available without guessing names. Multi-page fanout lets you request several result pages in one call with automatic deduplication. Validation catches common mistakes like passing an engine name to the category parameter. The URL reader handles static HTML, JSON, YAML, and TOML without a headless browser, with extraction modes for reading just headings or specific sections to save tokens on long documentation pages.
- GitHub stars
- 1
- tools
- 4
- transport
- STDIO
- env var
- 1
- last updated
- Jul 6, 2026
Tools
4 toolsPublic tool metadata for what this MCP can expose to an agent.
searchBroad web search across the full enabled engine pool.
Broad web search across the full enabled engine pool.
No parameter schema in public metadata yet.
search_on_enginesSearch using only the specified engines.
Search using only the specified engines.
No parameter schema in public metadata yet.
search_by_categorySearch within specific categories, running every engine tagged with each.
Search within specific categories, running every engine tagged with each.
No parameter schema in public metadata yet.
web_url_readFetch a URL and convert its HTML to clean Markdown.
Fetch a URL and convert its HTML to clean Markdown.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
SEARXNG_URLBase URL of the SearXNG instance (e.g. http://127.0.0.1:7979/). Defaults to http://127.0.0.1:8080 if unset; set this to the address of your running SearXNG.
Readme
searxng-deepdive
An MCP server for SearXNG designed for LLM agents doing real research. Four tools with agent-friendly schemas, multi-page result fanout, lightweight URL→Markdown reading, and tool descriptions generated dynamically from the live engine pool of your SearXNG instance.
Why another mcp-searxng?
Existing packages are minimal — most expose a single search(query) tool
with no way for the model to ask for more results, target specific engines,
or constrain by category. The richer ones bake static descriptions, so the
LLM never learns what's actually enabled on this instance. None of them
treat agent-tool-selection ergonomics as a design priority.
searxng-deepdive opens those knobs up:
Details
- Repository
- github.com/burakaydinofficial/searxng-deepdive
- Categories
- Documents & Knowledge, Search & Web Crawling
- Package
searxng-deepdive- Transport
- STDIO
- Registry
- MCP registry, active
Related Documents & Knowledge MCP servers
View all
Fodda Knowledge Graphspiers-fawkes/fodda-mcpExpert-curated knowledge, brand, research & earnings intelligence — 56 tools, 220+ graphs.1stars
Danbooru Tagsgamzadongza/danbooru-tags-mcpExtract tags from any Danbooru post and explore categories at a glance. Analyze character-specific tag frequencies to surface top traits and clothing patterns. 1stars
Brewers Almanackgregario/brewers-almanackBrewing knowledge MCP — beer styles, ingredients, off-flavours, water chemistry, recipes1stars
Groupdocs Metadata Mcpgroupdocs-metadata/groupdocs.metadata.mcpMCP server for GroupDocs.Metadata — read, search, write, and remove document metadata.1stars
Lambëhakimjonas/lambeShape-aware query language for structured data — JSON, YAML, TOML, HCL, CSV, Markdown.1stars
Silicon News Wirekillua-xiao/silicon-nexusSilicon News Wire: curated public briefs in HTML, JSON, and Markdown. Read-only.0stars