Terminal and OS · MCP server
Flightclaw: MCP server, setup and security
Flightclaw is an open-source MCP server that lets an AI agent search around 300 airlines and book flights using a checkout link. Its repository has 75 stars and its last commit is from October 5, 2026 and it is licensed under MIT.
| Adoption (stars) | 19/40 | |
|---|---|---|
| Maintenance | 30/30 | |
| Framework (licence, registry, official) | 21/30 |
What Flightclaw does
According to its repository: “Search ~300 airlines and book flights with a checkout link. OAuth sign-in by email code.”
An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. Flightclaw is listed under Terminal and OS, a category of 115 servers in the directory, where it ranks #72 by stars.
Topics declared by the repository: flights, openclaw, claude-code, claude-desktop, flight-search, flight-tracker.
Installing and connecting Flightclaw
Distribution modes declared in the official MCP registry:
- remote server (streamable-http): you connect to it by URL, with nothing to install locally
Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: Python.
Security: what to check
An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.
Points found for Flightclaw:
- System access: the Terminal and OS category gives the agent control over files, a terminal, code or a browser. A booby-trapped instruction in content the agent reads (prompt injection) can then turn into an action.
Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.
Project activity and maintenance
Created on February 10, 2026, the flightclaw/agents repository has 75 stars and 13 forks, with 6 open issues. It has more stars than 61% of the servers in the directory. It received changes this month. Version published in the registry: 1.0.0 (September 26, 2026).
Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.
Verdict
Flightclaw is a reasonable choice; check the points below before connecting it.
Strengths
- Active project: recent commit
- Listed in the official MCP registry
- Usable remotely, without installation
- Permissive licence (MIT)
Avoid if…
- You cannot isolate the agent (sandbox, container)
Alternatives
- Oh My Posh Validator23.6K ★
- REA377.2K ★
- XERJ15.2K ★
- Windows MCP10.2K ★
- Microsoft Learn MCP2K ★
- NotFair4.1K ★
Learn more
Frequently asked questions
How do I install Flightclaw?
Flightclaw is distributed as a remote server. Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of flightclaw/agents.
Is Flightclaw free?
The code is published under the MIT licence and can be used free of charge.
Is Flightclaw safe?
Points to watch: system access. Give it minimum rights and approve sensitive actions.
Is it an official server?
It is published in the MCP registry under the verified namespace com.flightclaw, which shows the publisher controls that domain.
What are the alternatives to Flightclaw?
In the same category: Oh My Posh Validator, REA, XERJ, and Windows MCP. Oh My Posh Validator and REA score higher on our grid.
Related articles
- Build your own MCP server in 30 minutesOctober 24, 2026
- Automate your inbox with an AI agentOctober 18, 2026
- MCP, A2A, and tool calling: agent protocols explainedOctober 17, 2026
- Build an AI agent with n8n, without codingOctober 16, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score