automationnation-mcpSAFE
MCP server for AI agents: Google Flights, Hotels, Shopping, News, Images, Videos, Jobs, Trends, Maps leads, Ads Transparency, YouTube transcripts, app reviews and AI visibility, via Apify.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
AutomationNation MCP server: Google Flights, Hotels, Shopping, News, Jobs, Trends, Maps leads, YouTube transcripts and more for AI agents
[](https://glama.ai/mcp/servers/retracn/automationnation-mcp) [](LICENSE) [](https://registry.modelcontextprotocol.io/v0/servers?search=io.github.retracn)
An MCP server with 18 data tools for Claude, ChatGPT, Cursor, VS Code and other AI agents. Each tool runs one of AutomationNation's Apify Actors on your Apify account and returns compact JSON the agent can use straight away: flight fares, hotel prices, product prices, news, jobs, search trends, local business leads, competitors' ads, YouTube transcripts, app reviews and AI-search visibility.
- Purpose-built tools: short, documented inputs (
origin,destination,departure_date...) instead of raw scraper schemas, and outputs trimmed to the fields an agent needs. - Pay per result, no subscription: usage is billed by each Actor on your Apify account (prices below). A free Apify account includes monthly credit.
- Safe by default: every run carries a spending cap of about 3x its expected cost; long runs return partial results with a
run_idinstead of timing out. - Works without a token for discovery: tools are listed before you configure anything, so clients and registries can inspect them.
Try it without installing anything: add https://mcp.apify.com/?tools=automationnation/data-tools-mcp-server as a connector in Claude, ChatGPT or any remote-MCP client, sign in with Apify, and ask something like "find nonstop flights from London to New York on 12 November". Other ways to run it are under Install.
Tool
37ade54c46adOBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-smoke-test --env APIFY_API_TOKEN=${APIFY_API_TOKEN} --env APIFY_TOKEN=${APIFY_TOKEN} -- npx -y [email protected]{
"mcpServers": {
"mcp-smoke-test": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"APIFY_API_TOKEN": "${APIFY_API_TOKEN}",
"APIFY_TOKEN": "${APIFY_TOKEN}"
}
}
}
}Exposed tools (1)
0 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_run_results | write | Fetch the results of a run that was still going when its tool returned. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (8)
const actors = JSON.parse(readFileSync(new URL('../../marketing/actors.json', import.meta.url), 'utf8'));base = `http://127.0.0.1:${mock.address().port}`;up = await fetch(`http://127.0.0.1:${port}/`, { headers: { 'x-apify-container-server-readiness-probe': '1' } }).then((r) => r.ok).catch(() => false);await anon.connect(new StreamableHTTPClientTransport(new URL(`http://127.0.0.1:${port}/mcp?tools=travel`)));await user.connect(new StreamableHTTPClientTransport(new URL(`http://127.0.0.1:${port}/mcp`), { requestInit: { headers: { Authorization: 'Bearer user-token' } } }));apify, zod
@modelcontextprotocol/sdk, zod, @anthropic-ai/mcpb, esbuild
apify, zod
Gates applied: no_behavioural_pass.
37ade54c46adfull audit observations/trust-audit/mcp-server/retracn__automationnation-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 37ade54c46ad | SAFE | B | 89 | first audit |
Questions
What is the automationnation-mcp MCP server?
MCP server for AI agents: Google Flights, Hotels, Shopping, News, Images, Videos, Jobs, Trends, Maps leads, Ads Transparency, YouTube transcripts, app reviews and AI visibility, via Apify.
What tools does automationnation-mcp expose?
1 in total: 0 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is automationnation-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does automationnation-mcp need?
It reads APIFY_API_TOKEN and APIFY_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does automationnation-mcp run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as mcp-smoke-test at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (37ade54c46ad), read on 2026-10-11. The repository is watched and re-audited when it changes.