--- title: "Brave Search MCP Server: Web, News, Images and AI Context" url: "https://mcpshelf.co/servers/brave-search" description: "Brave's official server gives an assistant web, news, image, video and local search from Brave's own index, plus context for grounding. Key and setup." updated: "2026-10-27" site: "MCP Shelf" --- # Brave Search MCP > Web, news, image, video and place search from Brave's own index. Source: https://mcpshelf.co/servers/brave-search Markdown: https://mcpshelf.co/servers/brave-search.md Generated: 2026-10-27T13:28:45.355Z ## Facts - **Name:** Brave Search MCP - **Tagline:** Web, news, image, video and place search from Brave's own index. - **Description:** Brave Search MCP is Brave's official server that gives an assistant web, news, image, video and local search from Brave's own index, plus AI summaries and page context. - **Repository:** https://github.com/brave/brave-search-mcp-server - **Package:** @brave/brave-search-mcp-server 2.1.4 (npm) - **Install:** `claude mcp add brave-search -e BRAVE_API_KEY=YOUR_BRAVE_API_KEY -- npx -y @brave/brave-search-mcp-server --transport stdio` - **Transport:** stdio (local) - **Auth:** Needs `BRAVE_API_KEY` - **Tools exposed:** 8: `brave_web_search`, `brave_local_search`, `brave_video_search`, `brave_image_search`, `brave_news_search`, `brave_summarizer`, `brave_llm_context`, `brave_place_search` - **Category:** Browser and web data (https://mcpshelf.co/categories/browser-and-web) - **Stats:** 1.5K GitHub stars, last commit 27 Oct 2026, 0 upvotes on MCP Shelf - **Install check:** Started in our test - **Listed:** 2026-10-27 - **Page updated:** 2026-10-27 ## Full description ### What is Brave Search MCP? **Brave Search MCP is Brave's official server that gives an assistant web, news, image, video and local search from Brave's own index, plus AI summaries and page context.** Brave maintains this server for its Search API, which runs on Brave's independent web index rather than reselling another engine. The model gets separate tools for web, news, video and image search, a place search that finds businesses and points of interest around a location, and a summariser that turns a web search into a short answer with sources. The newest tool, LLM context, skips the list of links and returns pre-extracted passages from the top pages, sized to a token budget you set, which saves a round of fetching. You can switch individual tools off with an environment variable if you only want one or two of them in the prompt. | | | | --- | --- | | Made by | Brave Software (brave/brave-search-mcp-server) | | GitHub | https://github.com/brave/brave-search-mcp-server | | Licence | MIT | | npm package | [@brave/brave-search-mcp-server](https://www.npmjs.com/package/@brave/brave-search-mcp-server) 2.1.4 (17 Sept 2026) | | GitHub stars | 1.5K | | Last commit | 27 Oct 2026 | | Tools | 8 | | Runs on | Your computer | | Install check | Started in our test | | Category | [Browser and web data](https://mcpshelf.co/categories/browser-and-web) | | Setup checked | 27 Oct 2026 | | Page updated | 27 Oct 2026 | **Our check:** We ran this exact config on 27 Oct 2026: it started and answered with 8 tools. #### MCP Shelf take > We started Brave Search on our own test machine on 27 Oct 2026 and it answered with 8 tools. None of them is read-only, so keep "ask before each tool call" on. Every tool comes with a useful description, none says whether they change things, and the tool list costs about 2,200 tokens of context before you ask a thing. It sits 12th of 13 in its category on our shelf by GitHub stars (1.5K). — MCP Shelf tests (numbers from our own runs), tested on 27 Oct 2026 ### What tools does Brave Search MCP have? We listed 8 tools on 27 Oct 2026. 0 only read; the rest can change things or run commands. | Tool | Kind | What it is for | | --- | --- | --- | | `brave_web_search` | changes | Searches the web with filters for country, language, freshness and SafeSearch, and can return a summary key. | | `brave_local_search` | changes | Finds local businesses with ratings and opening hours. Needs a higher plan, and falls back to web search otherwise. | | `brave_video_search` | changes | Searches for videos and returns titles, lengths and thumbnails. | | `brave_image_search` | changes | Searches for images and returns their links and sizes. | | `brave_news_search` | changes | Searches recent news, the last day by default. | | `brave_summarizer` | changes | Turns a web search made with summary on into a short answer with sources. | | `brave_llm_context` | changes | Returns ready-made passages from the top pages for a query, within a token budget you set. | | `brave_place_search` | changes | Finds points of interest around coordinates or a named place, with addresses, hours and ratings. | #### How clearly it describes its tools 8 of 8 tools have a description and 0 of 8 say whether they change things. The tool list takes at least ~2,200 tokens of context. No tool says whether it only reads or can change things, so your client treats them all alike: keep approvals on. ### How do I install Brave Search MCP? #### What you need first - A Brave Search API key from the Brave API dashboard - Node.js, or Docker #### Claude Code Where: Your terminal, in the project folder ```bash claude mcp add brave-search -e BRAVE_API_KEY=YOUR_BRAVE_API_KEY -- npx -y @brave/brave-search-mcp-server --transport stdio ``` Put your own key in place of YOUR_BRAVE_API_KEY. The server needs Node.js 22 or newer; Brave's Docker image, mcp/brave-search, is the alternative. #### Cursor Where: ~/.cursor/mcp.json, or .cursor/mcp.json in a project ```json { "mcpServers": { "brave-search": { "command": "npx", "args": [ "-y", "@brave/brave-search-mcp-server", "--transport", "stdio" ], "env": { "BRAVE_API_KEY": "YOUR_BRAVE_API_KEY" } } } } ``` #### Claude Desktop Where: claude_desktop_config.json (Settings → Developer → Edit Config) ```json { "mcpServers": { "brave-search": { "command": "npx", "args": [ "-y", "@brave/brave-search-mcp-server", "--transport", "stdio" ], "env": { "BRAVE_API_KEY": "YOUR_BRAVE_API_KEY" } } } } ``` #### VS Code Where: .vscode/mcp.json in your project ```json { "servers": { "brave-search": { "type": "stdio", "command": "npx", "args": [ "-y", "@brave/brave-search-mcp-server", "--transport", "stdio" ], "env": { "BRAVE_API_KEY": "YOUR_BRAVE_API_KEY" } } } } ``` Brave's VS Code example asks for the key as a password input, so it never sits in the file. Use the same inputs block with this npx command or with the Docker image. #### Windsurf Where: ~/.codeium/windsurf/mcp_config.json ```json { "mcpServers": { "brave-search": { "command": "npx", "args": [ "-y", "@brave/brave-search-mcp-server", "--transport", "stdio" ], "env": { "BRAVE_API_KEY": "YOUR_BRAVE_API_KEY" } } } } ``` #### ChatGPT Where: Not supported ChatGPT only connects to remote servers by URL. This one runs on your computer, so use Claude, Cursor or VS Code. Some tools, such as local search and extra snippets, need a higher Brave plan; the rest work on the basic one. To keep only some tools, set BRAVE_MCP_ENABLED_TOOLS to a space-separated list, for example "brave_web_search brave_news_search". Checked against the project's own install docs on 27 Oct 2026: https://github.com/brave/brave-search-mcp-server#readme, https://brave.com/search/api/ ### How do I configure Brave Search MCP? | Setting | Kind | Required | What it does | | --- | --- | --- | --- | | `BRAVE_API_KEY` | env | yes | Your Brave Search API key. | | `BRAVE_API_KEY_FILE` | env | no | Path to a file that holds the key, for Docker secrets. Wins over BRAVE_API_KEY. Example: `/run/secrets/brave_key` | | `BRAVE_MCP_ENABLED_TOOLS` | env | no | Space-separated list of the only tools to load. Example: `brave_web_search brave_news_search` | | `BRAVE_MCP_DISABLED_TOOLS` | env | no | Space-separated list of tools to leave out. Example: `brave_image_search brave_video_search` | | `BRAVE_MCP_TRANSPORT` | env | no | stdio (the default since version 2) or http. Example: `stdio` | | `BRAVE_MCP_HOST` | env | no | Where the HTTP transport listens. Default 127.0.0.1; use 0.0.0.0 only inside a container. Example: `127.0.0.1` | | `BRAVE_MCP_PORT` | env | no | Port for the HTTP transport. Default 8080. Example: `8080` | ### What can Brave Search MCP read and change? **It can read** - Search results from the Brave Search API **It can change** - Nothing. Each call uses part of your Brave API allowance. **Safer setup:** It is read-only. To keep costs and context down, load only the search types you use with BRAVE_MCP_ENABLED_TOOLS. ### Good for - Giving an assistant fresh search results with dates and sources - Pulling recent news on a topic - Grounding answers in page text without a separate scraper ### Brave Search MCP not working? Common fixes **The server starts an HTTP port instead of talking to the client** Older 1.x versions defaulted to HTTP. Use version 2 or later, or pass --transport stdio. **Local search returns ordinary web results** Local search needs a higher Brave plan. Without it, the tool falls back to web search. **401 or 422 errors** Check that BRAVE_API_KEY holds the key itself, with no quotes or spaces, and that your plan covers the endpoint. **Image results no longer include the picture data** Version 2 returns image links only, to save time and context. Fetch an image by its link if you need it. ### What are the alternatives to Brave Search MCP? | Server | What it does | Tools | Runs on | Licence | Stars | | --- | --- | --- | --- | --- | --- | | [Brave Search MCP](https://mcpshelf.co/servers/brave-search) | Web, news, image, video and place search from Brave's own index. | 8 | Your computer | MIT | 1.5K | | [Playwright MCP](https://mcpshelf.co/servers/playwright) | Microsoft's browser automation server: navigate, click, type, read. | 25 | Your computer | Apache-2.0 | 38.7K | | [Firecrawl](https://mcpshelf.co/servers/firecrawl) | Scrape pages, crawl sites and search, returned as clean Markdown. | 28 | Your computer or hosted | MIT | 7.7K | | [Exa](https://mcpshelf.co/servers/exa) | Search built for AI: web results, page contents and code examples. | 2 | Hosted or your computer | MIT | 5.2K | | [Bright Data](https://mcpshelf.co/servers/bright-data) | Search and scraping through Bright Data, for sites that block ordinary requests. | 32 | Hosted or your computer | MIT | 2.7K | | [SearXNG](https://mcpshelf.co/servers/searxng) | Web search through your own SearXNG instance: no vendor, no API key. | 4 | Your computer | MIT | 1.3K | ### Brave Search MCP FAQ #### How do I add Brave Search MCP to Claude Code? Get a key from the Brave Search API dashboard, then run claude mcp add brave-search with -e BRAVE_API_KEY set to it, followed by npx -y @brave/brave-search-mcp-server --transport stdio. #### How do I set up Brave Search in Claude Desktop or Cursor? Add an entry that runs npx -y @brave/brave-search-mcp-server with BRAVE_API_KEY in env, or Brave's Docker image mcp/brave-search with the key passed through -e. Restart the app afterwards. #### Is Brave Search MCP the official Brave server? Yes. Brave maintains it in its own GitHub organisation and publishes it on npm as @brave/brave-search-mcp-server. #### Is Brave Search MCP free? The server is free under the MIT licence, but every search goes through the Brave Search API, which Brave bills according to your plan. Check Brave's API page for current prices. #### Does Brave use Google or Bing results? No. Brave Search runs on its own independent index, so its results can differ from what Google or Bing show for the same query. #### Which Brave tool should I use for grounding answers? brave_llm_context. It returns passages from the matching pages rather than a list of links, so the model does not need to fetch each one. #### Why does brave_local_search return normal web results? Local and place results need a higher Brave plan. Without it the tool falls back to ordinary web search. #### Does Brave Search MCP work with ChatGPT? Not as set up here, because ChatGPT only connects to servers by public URL. The server has an HTTP mode, but its endpoint has no authentication, so only expose it behind your own protection. Full docs on GitHub: https://github.com/brave/brave-search-mcp-server ## Notes for agents Fetch these instead of parsing the HTML page: - llms.txt: https://mcpshelf.co/llms.txt - llms-full.txt: https://mcpshelf.co/llms-full.txt - ai.txt: https://mcpshelf.co/ai.txt - Full catalog (.md): https://mcpshelf.co/catalog.md - API spec: https://mcpshelf.co/openapi.json - MCP server: https://mcpshelf.co/mcp - MCP manifest: https://mcpshelf.co/.well-known/mcp.json - Developer docs: https://mcpshelf.co/developers MCP endpoint (Streamable HTTP, no key): https://mcpshelf.co/mcp. REST API: https://mcpshelf.co/api/v1.