Webshift
A Rust-built MCP server that cleans web content for LLM consumption. Exposes three tools: webshift_query runs a full search pipeline (query, fetch, HTML strip, BM25 rerank, optional summarization), webshift_fetch grabs and cleans a single page, and webshift_onboarding returns configuration hints. It enforces strict token budgets at every stage so you don't flood the context window with navigation menus and ad scripts. Supports eight search backends including self-hosted SearXNG, Brave, Tavily, and Google. Ships as a single static binary with no runtime dependencies. Reach for this when you need deterministic, budget-controlled web search for agents without the noise of raw HTML or the overhead of a Python stack.
- GitHub stars
- 7
- tools
- 3
- last updated
- Mar 26, 2026
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
webshift_queryFull search pipeline: search + fetch + clean + rerank + (optional) summarize
Full search pipeline: search + fetch + clean + rerank + (optional) summarize
No parameter schema in public metadata yet.
webshift_fetchSingle page fetch and clean
Single page fetch and clean
No parameter schema in public metadata yet.
webshift_onboardingReturns a JSON guide for the agent (budgets, backends, tips)
Returns a JSON guide for the agent (budgets, backends, tips)
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 languageReadme
WebShift
What is WebShift
WebShift is a Rust library and MCP server that shifts noisy web pages into clean, right-sized text for LLM consumption.
Raw HTML is mostly junk: scripts, ads, navigation menus, cookie banners, tracking pixels. Feeding it directly to an LLM floods the context window with tens of thousands of useless tokens and leaves no room for reasoning. WebShift strips all that noise, sterilizes the text, and enforces strict
Details
- Repository
- github.com/annibale-x/webshift
- Category
- Search & Web Crawling
- Registry
- MCP registry, active
More from annibale-x
Related Search & Web Crawling MCP servers
View all
Arxiv Mcp Servercyanheads/arxiv-mcp-serverSearch arXiv, fetch paper metadata, and read full-text content.7stars
Webshiftx-hannibal/webshiftRust MCP server for denoised web search — fetch, clean, and rerank web content for AI agents.7stars
Webshiftx-monk/webshiftRust MCP server for denoised web search — fetch, clean, and rerank web content for AI agents.7stars
Hermes Atlas Mcpksimback/hermes-atlas-mcpSearch and fetch 100+ Hermes Agent tools, skills, plugins, and integrations from hermesatlas.com.6stars
grokipedia-mcpskymoore/grokipedia-mcpSearch and retrieve Grokipedia articles with filters, full content, and citations. Explore related pages and extract sections to quickly gather relevant knowled6stars
Kwp Lab Rss Reader Mcpkwp-lab/rss-reader-mcpTrack and browse RSS feeds with ease. Fetch the latest entries from any feed URL and extract full…5stars