Is Apify MCP server safe?
What Apify MCP server does
The Apify MCP server lets AI agents run Actors from Apify Store, which are ready-made scrapers, crawlers and automation tools, to extract data from websites, search engines, maps and other sources. It is published in the apify/apify-mcp-server repository, with a hosted endpoint at mcp.apify.com and a local npm package, @apify/actors-mcp-server. It calls the Apify platform with an APIFY_TOKEN or through payment options (AGI, x402, Skyfire), and Actor runs can be paid. Before installing, use --tools to expose only the Actors you need, and set --telemetry-enabled=false if you do not want telemetry and Sentry error tracking.
- Possible command injection (exec with dynamic command)
- Node.js shell/command execution
- MCP server launches a host command
What to do: Nothing here argues against installing it. Grant the capabilities it lists only if you expect the tool to need them.
Apify MCP server is an MCP server analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators, though 1 risky construct is reported for review. It can: filesystem read, filesystem write, mcp tools detected, network egress and shell execution — capabilities are what the code can do, not a verdict on intent. Risk score 20/100 (low).
@apify/
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 Apify MCP server's authors. Report a false positive.
Behavioral traits
How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.
Findings (7)
The code builds an OS command out of values that can change at runtime, then runs it through a shell.
const versionString = execSync(`pnpm view ${PACKAGE_NAME} versions --json`, { encoding: 'utf8' });Why it matters: If any of those values come from untrusted input, an attacker can run their own commands on the machine.
Fix: Use execFile/spawn with an argument array instead of exec; never build a shell command string from external input.
An MCP server entry launches a command on your host.
Why it matters: Trusting the manifest means running that binary — verify what it is and where it comes from.
Fix: Verify the launched command and its source before trusting this MCP server configuration.
The component can run operating-system commands or spawn processes.
import { execSync } from 'node:child_process';const versionString = execSync(`pnpm view ${PACKAGE_NAME} versions --json`, { encoding: 'utf8' });import { execSync } from 'node:child_process';rawBranch = execSync('git rev-parse --abbrev-ref HEAD', {import { spawn } from 'node:child_process';const child = spawn(cmd, args, {Why it matters: Powerful and often legitimate — confirm the commands aren't built from untrusted input.
Fix: Confirm the command and its arguments are fully controlled and not derived from untrusted input; prefer execFile with an argument array.
The component reads files from disk.
const cssContent = await fs.readFile(args.path, 'utf8');
Why it matters: Usually legitimate, but worth confirming it can't be steered into reading sensitive files.
Fix: Confirm which files are read and that paths cannot be influenced by untrusted input to reach sensitive locations.
The component writes or deletes files on disk.
fs.writeFileSync(outPath, `${JSON.stringify(testCases, null, 2)}\n`);await fs.rm(distPath, { recursive: true, force: true });Why it matters: Usually legitimate, but worth confirming the paths can't be controlled by untrusted input.
Fix: Confirm which files are written/deleted and that paths cannot be influenced by untrusted input.
The component makes outbound network requests.
import type { AxiosRequestConfig, AxiosResponse } from 'axios';import { isAxiosError } from 'axios';return apifyClient.httpClient.axios.request<unknown>({const response = await handler.fetch(request, options);
async fetch(input: Request | URL | string, init?: RequestInit) {return fetch(input, { ...init, headers });const response = await fetch(url, {import type { AxiosResponse } from 'axios';import type { AxiosResponse } from 'axios';import { isAxiosError } from 'axios';const response = await fetch(APIFY_API_OPENAPI_URL, { signal: AbortSignal.timeout(SPEC_DOWNLOAD_TIMEOUT_MS) });import { isAxiosError } from 'axios';const result = (await catchNotFound(fetch(safeId))) ?? undefined;
const resource = await fetch(toSafeResourceId(idOrName));
return fetch(`~${idOrName.trim()}`);import type { AxiosResponse } from 'axios';import { isAxiosError, isCancel } from 'axios';const response = await apifyClient.httpClient.axios.request<AsyncIterable<Buffer>>({return (apifyClient as unknown as { httpClient?: { axios?: AxiosInstanceLike } }).httpClient?.axios;log.warning('[x402] Failed to access apify-client axios internals — payment header capture disabled');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.
An MCP tool surface (manifest or tool definitions) was found.
"mcpServers": {"tools": {"type": "node",
const transport = new StreamableHTTPServerTransport({this.server = new Server(getServerInfo(), {this.server.setRequestHandler(ListToolsRequestSchema, async () => {this.server.setRequestHandler(CallToolRequestSchema, async (request, extra) => {this.server = new Server(getServerInfo(), {const transport = new StdioServerTransport();
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 Apify MCP server.
Maintain Apify MCP server?
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.
Check your own component
Run the same evidence-backed scan on any MCP server, agent skill, or package.
Scan your own componentHow we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →