Is Exa MCP server safe?

exa-mcp-server is an AI npm_package analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators, though 2 risky constructs are reported for review. It can: install time execution and mcp tools detected — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).

exa-mcp-server 3.2.1

npm_package · https://github.com/exa-labs/exa-mcp-server

LOW

0

/ 100 malicious-risk

Snapshot · scanned Jun 23, 2026 · exa-mcp-server@3.2.1 · engine 0.18.0 / ruleset 19

No malicious indicators - review capabilities before installing

Notable — review in context (capabilities are not malware):

npm prepare hook
MCP tool surface detected

No malicious indicators found by static analysis.

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

install time executionmcp tools detected

Findings (2)

MEDIUMnpm prepare hookST-INSTALL-NPM-PREPARE

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

package.json:43-43

"prepare": "npm run build:stdio",

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.

LOWMCP tool surface detectedST-MCP-DETECTED

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

.claude-plugin/plugin.json:10-10

"mcpServers": {

gemini-extension.json:5-5

"mcpServers": {

server.json:1-1

llm_mcp_docs.txt:1211-1211

const server = new Server({

llm_mcp_docs.txt:1592-1592

const server = new Server({

llm_mcp_docs.txt:1936-1936

const server = new Server({

llm_mcp_docs.txt:2424-2424

const server = new Server({

llm_mcp_docs.txt:2810-2810

mcp = FastMCP("example-server")

llm_mcp_docs.txt:2812-2812

@mcp.tool(

llm_mcp_docs.txt:2922-2922

const server = new Server({

llm_mcp_docs.txt:3007-3007

const server = new Server({

llm_mcp_docs.txt:3177-3177

const server = new Server({

llm_mcp_docs.txt:6096-6096

mcp = FastMCP("weather")

llm_mcp_docs.txt:6141-6141

@mcp.tool()

llm_mcp_docs.txt:6160-6160

@mcp.tool()

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

Fix: Review the declared MCP tools and their permissions.

Check your own component

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

Scan your own component

Or get notified if this component's risk changes:

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