
Mcp Webgate
Solves the context window explosion problem that happens when AI agents naively fetch web pages. Exposes three MCP tools: webgate_query for full search cycles (SearXNG, Brave, Tavily, Exa, or SerpAPI backends), webgate_fetch for single URL retrieval, and webgate_onboarding for usage guidance. Strips HTML down to readable text with lxml parsing, hard-caps every response to prevent token blowouts, and optionally routes results through a local LLM for summarization. The real win is parallel fetch with BM25 reranking: a 13-page search that would dump 1.3 million tokens of raw HTML gets compressed to under 2,000 tokens of structured Markdown with citations. Built for Claude Desktop, Zed, Cursor, and CLI agents where a single unfiltered page can wipe your entire conversation history.
- GitHub stars
- 3
- tools
- 3
- transport
- STDIO
- last updated
- Mar 24, 2026
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
webgate_fetchRead a single page: pass the URL and get back the cleaned text, up to max_query_budget characters.
Read a single page: pass the URL and get back the cleaned text, up to max_query_budget characters.
No parameter schema in public metadata yet.
webgate_queryRuns a full search cycle (search, fetch and clean) for one or several queries and returns cleaned, ranked results.
Runs a full search cycle (search, fetch and clean) for one or several queries and returns cleaned, ranked results.
No parameter schema in public metadata yet.
webgate_onboardingReturns a JSON guide explaining how to use webgate effectively.
Returns a JSON guide explaining how to use webgate effectively.
No parameter schema in public metadata yet.
Sponsors
Readme
mcp-webgate
Web search that doesn't wreck your AI's memory.
mcp-webgate is an MCP server that gives your AI clean, bounded web content — across all major AI clients:
- IDEs: Claude Desktop, Claude Code, Zed, Cursor, Windsurf, VSCode
- CLI Agents: Gemini CLI, Claude CLI, custom agents
🌱 A Gentle Introduction
What is mcp-webgate? When your AI uses a standard "fetch URL" tool, it gets the raw HTML of the page — ads, menus, scripts, cookie banners and all. A single news article can dump 200,000 tokens of garbage into the AI's memory, wiping out your entire conversation.
Details
- Repository
- github.com/annibale-x/mcp-webgate
- Categories
- AI & LLM Tools, Search & Web Crawling
- Package
mcp-webgate- Transport
- STDIO
- Registry
- MCP registry, active