MCP server CX Codex

webshift — Claude Code MCP server: what it does, install

Q: How do I install webshift in Claude Code?

Install the binary with `cargo install webshift-mcp`. The resulting executable is named `mcp-webshift`.

webshift searches the web, removes HTML noise, and returns size-controlled text to an agent. Use it when raw page markup is too costly.

Open on GitHub

What webshift does

webshift is a Rust MCP server for turning web search results into compact text. Its pipeline can expand a query with an LLM, search through a configured backend, remove duplicate and binary URLs, fetch pages with size caps, clean HTML, and rerank results with BM25. The response is structured JSON.

The server exposes webshift_query, webshift_fetch, and webshift_onboarding. The first runs the search, fetch, cleanup, and ranking flow; the second handles one page. Supported backends include SearXNG, Brave, Tavily, Exa, SerpAPI, Google, Bing, and HTTP. The setup example starts SearXNG with docker run -d -p 8080:8080 searxng/searxng.

Install the native binary with Cargo; its executable name is mcp-webshift. webshift parses static HTML and does not run JavaScript, so it cannot act as a headless browser for JavaScript-heavy SPAs.

What it helps with

search the web from an AI agent
strip ads, scripts, and navigation from HTML
cap page and total response size
rerank sources with BM25
fetch clean text from a single URL

Example prompts for the agent

Use webshift_query to research this topic, keep the relevant sources, and summarize them with inline citations.
Run webshift_fetch for this URL and return the page text without navigation or scripts.
Call webshift_onboarding and show the available backends and budget guidance.

How to install webshift

Install

The MCP registry has no launch command for it: see the repository README

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about webshift

How do I install webshift in Claude Code?

Install the binary with cargo install webshift-mcp. The resulting executable is named mcp-webshift.

What does webshift do?

It searches for pages, fetches and cleans their HTML, limits the returned content, and ranks sources. Its MCP tools return structured JSON.

Can webshift handle JavaScript-heavy applications?

No. It parses static HTML and does not execute JavaScript, so it does not replace a headless browser for SPAs that render content dynamically.

Similar MCP servers

All MCP servers for Agent setup: memory, context, orchestration →

rag-retrieval OrchestKit A skill with ready-made retrieval-augmented generation patterns: hybrid search, HyDE, reranking, pgvector. Useful when you are wiring a RAG pipeline and want working recipes. CX Codex +1 1,500installs nemotron-retrieval-recipes NVIDIA Nemotron Team Helps plan, debug, tune, export, and deploy public NVIDIA Nemotron embedding and reranking retrieval recipes. Useful for fixing recall and ranking issues in search pipelines. CX Codex +1 2,000installs tavily-best-practices tavily-ai This skill gives an agent guidance for Tavily web search, content extraction, site crawling, and research. Use it when adding current web data to an agent workflow or RAG system. CX Codex +1 20,700installs exa-web-search-free sundial-org Adds Exa search through MCP for web information, code examples, and company research. Use it when an agent needs external context without an API key. CX Codex +1 2,800installs exa-search exa-labs This skill calls Exa Search through cURL or raw HTTP. Use it when an agent needs semantic web retrieval, domain filters, fresh page content, or structured results. CX Codex +1 1,400installs qdrant-search-quality official github Diagnoses why Qdrant returns irrelevant matches and points to ways to improve search quality. Useful after an embedding model change or as your data grows. 61installs