AgentPod is building a private, secure device for your AI agent.The AgentPod device is coming.Coming soonBe first
We checked this and rejected itsecurity

Travel Assistant MCP Server Ecosystem: why it is not safe to use

We found a hardcoded SerpAPI key in an example env script, so we recommend using your own secret and rotating any exposed key before deployment.

What we found

Our review did not find hidden instructions, remote code fetching, privilege escalation, or broad credential access in the inspected repository. The server appears to make ordinary requests to disclosed travel-related services, mainly SerpAPI and the National Weather Service, and writes results to local server-specific directories.

The item that affected our review was secret handling. We found what appears to be a hardcoded SerpAPI key in `servers/flight_server/env_template_visible.sh`. Even in a template or example file, an embedded API key can create avoidable security and operational risk if it is reused, copied into deployments, or left active longer than intended.

What to do instead

If you are evaluating or deploying this skill, use your own SerpAPI key via environment variables rather than any value included in repository files. Treat the visible key as exposed: rotate it if you control it, remove it from templates, and replace it with a placeholder that documents the required variable name. Before production use, review any sample scripts and local result storage paths to confirm they match your key management and data retention practices.

Want the same outcome, safely? Use our checked skill instead.

Source: https://github.com/skarlekar/mcp_travelassistant

We report what our security review found at the time we checked, with the goal of keeping people safe. Projects change; if a maintainer has since fixed this, we are glad to recheck it. Email hello@agentpod.com.

Copied to clipboard. Paste it into your AI (ChatGPT, Claude, or your agent) to add the skill.