Is Brave Search MCP server (GitHub) safe?

What Brave Search MCP server (GitHub) does

Brave's Brave Search MCP server integrates the Brave Search API for web, local business, place, image, video and news search, plus LLM context and AI summarization. It is published in the brave/brave-search-mcp-server repository and supports STDIO, the default since version 2.x, and HTTP transports. It sends queries to the Brave Search API using BRAVE_API_KEY, or a key read from the file named in BRAVE_API_KEY_FILE. Before installing, read the 1.x to 2.x migration notes on transport and response format changes, and prefer BRAVE_API_KEY_FILE if your setup supports mounted secrets.

No malicious indicators - review capabilities before installing

Notable — review in context (a capability is not a malicious indicator):

Node.js network egress
npm prepare hook
MCP tool surface detected

What to do: Nothing here argues against installing it. Grant the capabilities it lists only if you expect the tool to need them.

Brave Search MCP server (GitHub) is an MCP server analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators. It can: install time execution, mcp tools detected and network egress — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).

@brave/brave-search-mcp-server 2.1.4

GitHub repository, read as an npm package · https://github.com/brave/brave-search-mcp-server

LOW

/ 100 risk score

Snapshot · scanned Nov 13, 2026 · @brave/brave-search-mcp-server@2.1.4 · engine 1.1.0 / ruleset 100

Get notified when this component changes

Change alerts aren't live yet. Leave your email and we'll let you know when they launch. We use it only for this and delete it on request.

Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of Brave Search MCP server (GitHub)'s authors. Report a false positive.

Capabilities — what this component can do (not a risk score):

install time executionmcp tools detectednetwork egress

Behavioral traits

How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.

Tool surface

Tool Usage

Network egress

Interaction & Communication / Direct Communication

Supply-chain provenance risk

General Protections / Supply Chain

Findings (3)

Capabilitynpm prepare hooknot scored · severity mediumST-INSTALL-NPM-PREPARE

package.json has a 'prepare' script (runs on git/local installs and before publishing).

package.json:30

"prepare": "npm run format && npm run build",

Why it matters: Usually a build step, but confirm it doesn't fetch or run remote code.

Fix: Usually a legitimate build step; confirm it only builds and does not fetch or execute remote code.

CapabilityNode.js network egressnot scored · severity mediumST-NET-NODE

The component makes outbound network requests.

src/BraveAPI/index.ts:116

const response = await fetch(urlWithParams, { headers });

src/testUtils/agentCore.ts:83

const res = await fetch(`${baseUrl}/mcp`, {

Why it matters: Usually legitimate, but confirm the destinations are expected and no sensitive data leaves.

Fix: Confirm the destination hosts are expected and that no sensitive data is sent off-host.

CapabilityMCP tool surface detectednot scored · severity lowST-MCP-DETECTED

An MCP tool surface (manifest or tool definitions) was found.

server.json:1

src/jsonSchemaDialect.ts:63

mcpServer.server.setRequestHandler(ListToolsRequestSchema, async (request, extra) => {

src/protocols/http.ts:32

const transport = new StreamableHTTPServerTransport({

src/protocols/http.ts:45

transport = new StreamableHTTPServerTransport({

src/protocols/http.ts:50

transport = new StreamableHTTPServerTransport({

src/protocols/stdio.ts:5

const transport = new StdioServerTransport();

src/server.ts:8

const mcpServer = new McpServer(

src/tools/images/index.ts:43

mcpServer.registerTool(

src/tools/llm_context/index.ts:49

mcpServer.registerTool(

src/tools/local/index.ts:77

mcpServer.registerTool(

src/tools/news/index.ts:56

mcpServer.registerTool(

src/tools/place_search/index.ts:54

mcpServer.registerTool(

src/tools/summarizer/index.ts:71

mcpServer.registerTool(

src/tools/videos/index.ts:41

mcpServer.registerTool(

src/tools/web/index.ts:122

mcpServer.registerTool(

Why it matters: Just context — review which tools it offers and their permissions.

Fix: Review the declared MCP tools and their permissions.

How attackers abuse these capabilities

Interactive labs on the attack class behind the rules above. They show the technique, not anything found in Brave Search MCP server (GitHub).

Install Script lab

Maintain Brave Search MCP server (GitHub)?

Check the next package before your agent installs it

The free Claude Code plugin scans each npm, PyPI or MCP package with this report's open-source engine before the install command runs. It runs on your machine and needs no account.

Set up the plugin Or scan pull requests in CI with the GitHub Action

Check your own component

Run the same evidence-backed scan on any MCP server, agent skill, or package.

Scan your own component

How we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →