mcp-server-sequential-thinkingnpm
mcp-server-sequential-thinking is a confirmed malicious npm package (MAL-2026-5484) that steals credentials and exfiltrates sensitive data (malicious versions 0.0.1, 0.0.2). Do not install it — remove it immediately and rotate any exposed credentials.
Malicious code in mcp-server-sequential-thinking (npm)
What this malware does
Unscoped package impersonating the official @modelcontextprotocol/server-sequential-thinking MCP server. package.json declares postinstall: 'node index.js' and a bin entry mapping mcp-server-sequential-thinking to./index.js, so both npm install and npx mcp-server-sequential-thinking execute index.js automatically. index.js requires os/https/http and at lines 17-28 unconditionally POSTs a JSON payload containing os.hostname(), process.cwd(), the npm user-agent, Node version, and os.platform()/arch to https://npx-canary-log.vulnerable-live.workers.dev/log, a Cloudflare Workers endpoint controlled by the package author. The payload includes a trigger field that distinguishes postinstall vs bin-exec invocations, confirming the author intends to harvest both pathways. The package targets AI coding agents and developers who type the unscoped name expecting the official scoped MCP server. Although the README frames this as 'canary' research, installers do not consent, and host identifiers leave the machine to an attacker-controlled destination at install time.
Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be rotated immediately from a different computer. The package should be removed, but as full control of the computer may have been given to an outside entity, there is no guarantee that removing the package will remove all malicious software resulting from installing it.
Malicious versions
Indicators of compromise (SHA-256)
Detection & response playbook
Credential / info stealerFind it
Scan your lockfiles (package-lock.json, pnpm-lock.yaml, yarn.lock, requirements.txt, poetry.lock, etc.) and build artifacts for mcp-server-sequential-thinking (2 malicious versions). O3 Security's supply-chain scanner checks every dependency against known-malicious package intelligence at install time and in CI, flagging mcp-server-sequential-thinking across your stack and pipelines.
If you installed it — respond
mcp-server-sequential-thinking is built to steal secrets, so assume every credential the build or runtime could read is compromised. Remove it from your project and lockfile, then rotate ALL exposed secrets — npm/registry tokens, cloud keys, CI/CD secrets, SSH keys, and any .env values — from a known-clean machine. Audit logs for unauthorized use of those credentials.
Did it already run?
If mcp-server-sequential-thinking was ever installed, its post-install/runtime payload may have already executed. O3's L7 egress monitoring and runtime eBPF sensors detect the credential exfiltration or command-and-control callback after install and block the malicious outbound channel, so you catch and contain the actual compromise — not just the presence of the package.
How O3 protects you
O3 blocks mcp-server-sequential-thinking before install through its supply-chain scanner, and if it has already run, detects and severs the exfiltration or C2 callback at runtime through L7 egress monitoring and eBPF.
Frequently asked questions
Campaign
References
Credits
- Amazon Inspector · finder
- ReversingLabs · finder
Detect & block this
O3 blocks mcp-server-sequential-thinking-class packages before install and in CI — and if it already ran, its runtime egress monitoring catches the credential exfiltration and severs the channel.