api2aiBLOCK
💻⚒️ NPM dev tools and core parts for Full Stack Starter App & Docs 🚀DEMO
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
e47a6ba94e37OBSERVED · 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 create-starter-app --env AUTH_RESEND_KEY=${AUTH_RESEND_KEY} --env AUTH_SECRET=${AUTH_SECRET} --env AUTH_TRUSTED_ORIGINS=${AUTH_TRUSTED_ORIGINS} --env AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID} -- npx -y [email protected]{
"mcpServers": {
"create-starter-app": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"AUTH_RESEND_KEY": "${AUTH_RESEND_KEY}",
"AUTH_SECRET": "${AUTH_SECRET}",
"AUTH_TRUSTED_ORIGINS": "${AUTH_TRUSTED_ORIGINS}",
"AWS_ACCESS_KEY_ID": "${AWS_ACCESS_KEY_ID}"
}
}
}
}Exposed tools (9)
9 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Changelog | read | Only results about the changelog |
Home | read | Only results about the main documentation page |
IndieSaas | read | A modern SaaS starter built with Next.js, Drizzle, and Better Auth |
User | read | User management endpoints |
a.ts | read | File A |
getPageContent | read | Get the list of pages in the documentation. |
provideLinks | read | Provide links to articles found using the Web Search tool. This is compulsory and MUST be called after a web search, as it gives the user context on which URLs were used to generate the response. |
react | read | UI lib |
searchDocs | read | Search the documentation using the internal search server. |
Trust audit
BLOCKgrade F · trust 48/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (10 observation(s))
- Network
- declared (14 observation(s))
- Shell
- declared (5 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
cat > "$HOME/.aws/credentials" <<CREDS
echo "https://x-access-token:${GITHUB_TOKEN}@github.com" > "$HOME/.git-credentials"rm -rf ~/.docker/buildx
echo "Dokploy installed! Access at http://$(curl -s http://169.254.169.254/latest/meta-data/public-ipv4):3000"
icon.icns
icon.icns
logo-ispum-1.avif
logo-ispum-2.avif
logo-ispum-3.avif
let callback_url = format!(
if let Ok(url) = Url::parse(&callback_url) {let callback_url = format!(
if let Ok(url) = Url::parse(&callback_url) {echo "Dokploy installed! Access at http://$(curl -s http://169.254.169.254/latest/meta-data/public-ipv4):3000"
{ key: "users_logged_in", emoji: "🧑🤝🧑", label: "Logged in" },const SECRET = "a-long-random-shared-secret";
const API_KEY = 'sms_1234567890abcdef1234567890abcdef';
const API_KEY = 'sms_1234567890abcdef1234567890abcdef'; // Change to your API key
token: "mock-jwt-token-12345",
token: "mock-jwt-token-12345",
.vscodeignore
.directory
const { status, stdout } = exec(cmd)const { status, stdout } = exec(`node -p "process.version + ' ' + process.execPath"`)import { renderBadgeBlock } from '../../packages/template-git-repo/src/badges.js'Gates applied: no_behavioural_pass.
e47a6ba94e37full audit observations/trust-audit/mcp-server/opensourceagi__dev-tools-starter-agent.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 | e47a6ba94e37 | BLOCK | F | 48 | first audit |
Questions
What is the api2ai MCP server?
💻⚒️ NPM dev tools and core parts for Full Stack Starter App & Docs 🚀DEMO
What tools does api2ai expose?
9 in total: 9 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is api2ai safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (48/100) and found 4 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does api2ai need?
It reads AUTH_RESEND_KEY, AUTH_SECRET, AUTH_TRUSTED_ORIGINS, AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, BACKBLAZE_APPLICATION_KEY, BACKBLAZE_APPLICATION_KEY_ID, BETTER_AUTH_SECRET, CREDENTIALS_ENCRYPTION_KEY, DATABASE_AUTH_TOKEN, DOC_EDITS_ADMIN_PASSWORD and DOC_EDITS_SECRET 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 current is this page?
The grade is for one exact copy of the source (e47a6ba94e37), read on 2026-10-11. The repository is watched and re-audited when it changes.