Passenger
repo-search-mcp
- Found in
- Cursor
- Can reach
- src/
- Score
- 94
Gate 01 · Discovery Scan
NoFly is a shadow AI discovery tool built for AI agents. It finds every agent, MCP server, and tool running in your org, and shows which ones are risky before they cause a problem.
Passenger
repo-search-mcp
Passenger
pdf-wizard-mcp
Passenger
shell-helper
Finds agents from
Developers add AI agents and MCP servers every day, usually without telling security. A NoFly Discovery Scan shows you all of it in one place.
Coding assistants, internal bots, and the shadow AI nobody signed off on, with who runs each one and where.
Each server your agents connect to, and exactly what it can touch: files, secrets, the terminal, the network.
A score for every tool, checked against the NoFly list, with a plain explanation of why it's risky and what to do.
How a scan works
Link your repos, dev machines, or identity provider. Read-only.
NoFly finds every agent and tool, then checks each one against the NoFly list.
Get a report ranked by risk, with the fix for each finding and a summary you can share upward.
Discovery scan report
Example Co.
Sample
Passport control · Free
Look up any server before your agents load it. Public scores, no signup.
What's next
Discovery is the first checkpoint. Next, NoFly will let you set policy for every agent and stop risky actions while they run.
Checkpoint 1
Find and score every agent and tool.
Checkpoint 2
Approve and deny tools with one policy.
Checkpoint 3
Stop risky actions while agents run.
A shadow AI discovery tool finds the AI agents and tools people use at work without security sign-off. Many watch browser and SaaS traffic, which catches chat apps. NoFly also looks inside developer tooling, where coding agents like Claude Code and Cursor load MCP servers that can reach files, secrets, and the terminal.
Shadow AI is any AI agent or tool people use at work without the security team knowing about it. A NoFly Discovery Scan finds these agents and the MCP servers they connect to, so you can decide what stays.
An MCP server gives an AI agent new abilities, like reading files, running commands, or calling an API. A malicious or careless server can make an agent leak secrets or take actions nobody approved, and most security tools never see it because it happens inside the agent.
Look at what it can reach (files, secrets, the terminal, the network), who publishes it, and whether it sends data anywhere it does not declare. The NoFly list runs these checks for you and gives each server a public risk score.
No. The Discovery Scan is read-only. It reports what it finds and leaves your agents, tools, and settings as they are.
Coding assistants such as Claude Code, Cursor, GitHub Copilot, Windsurf, and OpenAI Codex, plus internal agents and bots that connect to MCP servers.
Yes. Anyone can look up an MCP server on the NoFly list and see its risk score, with no signup and no install.