Scientific research · MCP server
Paper preflight: MCP server, setup and security
Paper preflight is an open-source MCP server that lets an AI agent verify paper references, metadata and retraction status without LLM judgments. Its repository has 100 stars and its last commit is from October 15, 2026 and it is licensed under MIT.
What Paper preflight does
According to its repository: “Checks every reference of a LaTeX paper against Crossref, dblp, arXiv, DataCite, PubMed and OpenAlex records: whether each cited work exists, matches its metadata and was not retracted, with no LLM in the verdict.”
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. Paper preflight is listed under Scientific research, a category of 35 servers in the directory, where it ranks #7 by stars.
Topics declared by the repository: academic-writing, bibtex, citation-checker, citations, claude-code, hallucinated-citations.
Installing and connecting Paper preflight
Distribution modes declared in the official MCP registry:
- PyPI package (Python, started with
uvxorpip)
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. Listed systems: macOS, Windows, Linux.
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.
None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to Paper preflight. That does not replace reading the code.
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 October 3, 2026, the amos689/paper-preflight repository has 100 stars and 9 forks, with 0 open issues. It has more stars than 67% of the servers in the directory. It received changes this month. Version published in the registry: 1.0.0 (October 15, 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
Paper preflight is a reasonable choice; check the points below before connecting it.
Strengths
- Active project: recent commit
- Listed in the official MCP registry
- Permissive licence (MIT)
Alternatives
- Zotero MCP (54yyyu)5.5K ★
- ToolUniverse1.8K ★
- Idea reality MCP828 ★
- Research toolkit299 ★
- OmniSeek95 ★
- TinySearch233 ★
Learn more
Frequently asked questions
How do I install Paper preflight?
Paper preflight is distributed as PyPI package (Python, started with uvx or pip). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of amos689/paper-preflight.
Is Paper preflight free?
The code is published under the MIT licence and can be used free of charge.
Is Paper preflight safe?
No risk signal found (system access, secrets, licence, abandonment). As with any MCP server, keep rights minimal and read the code before sensitive use.
Is it an official server?
Nothing says so: it is a project published by amos689 on GitHub. Check who maintains it before giving it access.
What are the alternatives to Paper preflight?
In the same category: Zotero MCP (54yyyu), ToolUniverse, Idea reality MCP, and Research toolkit. Zotero MCP (54yyyu) scores 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