Brave Search MCP vs MCP Fetch Server

A side-by-side look at pricing, capabilities, pros, cons, and our editorial scores.

	Brave Search MCP MCP Servers	MCP Fetch Server MCP Servers
Tagline	Give any MCP client web and local search powered by the Brave Search API.	Official Model Context Protocol reference server that lets any MCP-compatible LLM fetch web pages and read them as clean markdown.
Category	MCP Servers	MCP Servers
Pricing	Freemium· Free: $0 USD · Team: $4 USD per user/month · Enterprise: $21 USD per user/month	Free· Free and open source (MIT License). No hosted tier; you run it locally via uvx, pip, or Docker.
Model	—	—
Editorial score	—	—
Use cases	Grounded web search inside Claude DesktopAgent fact-checking and citation lookupIDE-side research from Cursor or WindsurfLocal business and restaurant discoveryCheap RAG augmentation for small chatbotsMCP server learning and forkingPrivacy-respecting alternative to Google search in agents	Reading documentation pages inside Claude DesktopGrabbing a GitHub README before scaffolding a projectSummarising a long article for a chat agentChecking a package changelog during code reviewAnswering questions from a linked spec section by sectionFeeding a URL into an MCP-driven research agentPulling clean markdown for a note-taking workflowVerifying a citation URL inside an editorial pipeline
Pros	Two focused tools (web + local search) that are easy to reason about and stable to prompt against Small, single-file TypeScript implementation that's trivial to read, fork, or self-host Ships as both an npm package and a Docker image, with VS Code one-click install Backed by Brave's independent index, so results don't depend on Google/Bing rate limits or ToS Free tier covers 2,000 queries/month, enough for personal agents and prototyping MIT-licensed reference implementation from the MCP project itself Local-search fallback to web means agents rarely get an empty result set	Official reference implementation maintained in the modelcontextprotocol/servers repo — tracks the spec and won't rot behind third-party churn. Zero-install path via `uvx mcp-server-fetch`; Docker image and pip package also available for sandboxed or reproducible setups. HTML-to-markdown conversion produces context-window-friendly output instead of raw tag soup. `max_length` + `start_index` let a model chunk through long pages without blowing its context. Optional Node.js fallback swaps in a more robust HTML simplifier when present. First-class configuration for User-Agent, robots.txt obedience, and outbound proxy — practical knobs for real-world scraping etiquette. Works out of the box with every major MCP client (Claude Desktop, Claude Code, VS Code, Cursor, Zed, Continue).
Cons	Repository is archived (read-only since May 29, 2025) and no longer receives fixes or new features Superseded by Brave's own official server, which adds image/video/news/summarizer tools and HTTP transport Free tier is capped at 1 query per second, which throttles multi-step agents Local search is US-centric and quality varies sharply outside North America No streaming HTTP transport in this version, stdio only, which complicates remote/multi-tenant deployments Brave's index, while good, is smaller than Google's and can miss long-tail queries	No JavaScript rendering — SPAs, Cloudflare-challenged pages, and content loaded after DOMContentLoaded come back empty or as a shell. No built-in anti-bot handling; sites that block plain HTTP clients (many news sites, LinkedIn, X) will 403. Security caveat called out in the README: the server can reach local/internal IPs, so it is a genuine SSRF risk if exposed to an untrusted model or user. Single tool, single verb — for crawling, sitemap walks, or extracting structured data you need a heavier server like Firecrawl-MCP or a Playwright-based one. Truncation defaults to 5,000 characters; models that don't understand `start_index` can silently miss content below the fold.
Website	github.com	github.com

Pick Brave Search MCP if

✅ Two focused tools (web + local search) that are easy to reason about and stable to prompt against
✅ Small, single-file TypeScript implementation that's trivial to read, fork, or self-host
✅ Ships as both an npm package and a Docker image, with VS Code one-click install
✅ Backed by Brave's independent index, so results don't depend on Google/Bing rate limits or ToS

Pick MCP Fetch Server if

✅ Official reference implementation maintained in the modelcontextprotocol/servers repo — tracks the spec and won't rot behind third-party churn.
✅ Zero-install path via `uvx mcp-server-fetch`; Docker image and pip package also available for sandboxed or reproducible setups.
✅ HTML-to-markdown conversion produces context-window-friendly output instead of raw tag soup.
✅ `max_length` + `start_index` let a model chunk through long pages without blowing its context.

Compare a different pair →