paperdebugger

MCP server · GitHub · ★ 1.6k · graded 2026-10-22Source linked

A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing

No outside reports on file

Use PaperDebugger only with non-sensitive academic drafts until you verify how it handles data and what the individual agents can access.

Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for Paperdebugger helpful?

What it can access

  • Local filesNo local folder access notedLOW
  • Command executionNo shell command runner notedLOW
  • Network reachConnects to outside service APINOTED
  • CredentialsNo API token requiredLOW
  • Package sourceGitHub (PaperDebugger/paperdebugger)PUBLIC

Inferred from this listing’s public package details and description. Check the project’s source before installing.

Install

No npm or PyPI package is listed. Install from source: github.com/PaperDebugger/paperdebugger ↗

All setup options ↓

About Paperdebugger

PaperDebugger is a multi-agent system that helps academics write, review, and edit papers directly inside text editors. It uses AI agents working together to provide feedback, suggest improvements, and help polish academic writing.

Who it’s for

Academic researchers and students who want AI assistance for paper writing and editing integrated into their editor. It's designed for people working on academic documents who want collaborative review from multiple AI agents.

Alternatives

  • Overleaf: Cloud-based LaTeX editor with built-in collaboration and comment features for academic writing.
  • Grammarly: Browser extension and standalone app that checks grammar and style in real-time.
  • Writefull: Editor plugin specifically designed for academic writing feedback and language improvement.
  • Claude or ChatGPT with manual prompts: Use a general AI assistant directly for paper review without a specialized plugin.

Setup

Check these steps against the project’s own instructions before running anything.

Follow the project's README. The GitHub repository should contain installation instructions for setting up the MCP connector with your editor and AI tools.

Why this grade

CC — Moderate risk signals

Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.

Popularity and upkeep

34/100
GitHub stars
1.6k
Listing last refreshed
2026-10-29

These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.

Security reports

No reports found for this package in our research (last checked 2026-10-29).

Check a specific version →

Risks to watch for

  • Access to draft files: The system reads and analyzes your paper content, potentially including unpublished research or sensitive findings before you're ready to share them.
  • Prompt injection in text: An attacker could embed hidden instructions in citations or quoted text that trick the AI agents into behaving unexpectedly or leaking information.
  • Data retention unknown: It's unclear whether analyzed papers are stored, logged, or used to train models—check the project's privacy policy if one exists.
  • Multi-agent coordination risks: Multiple AI agents working together could amplify mistakes or unexpected behavior more than a single system.
  • Editor plugin risks: Like any editor extension, it runs in your editing environment and could theoretically access other files if misconfigured.

How to lower the risk

Least-privilege permissions

  • Grant the connector access only to your papers folder, not your entire home directory.
  • Review what file types and directories the plugin can read.

Network isolation

  • Check whether agents send paper content to external servers or only process locally.
  • Use network monitoring tools to watch outgoing connections during use.

Monitoring

  • Enable logging in your editor to see what the MCP connector accesses.
  • Regularly audit which files have been read by the plugin.

Red flags to watch for

  • Unexpected uploads or network traffic when using the system.
  • Slowdowns or crashes that suggest background processing is running.
  • Missing or vague privacy documentation on the GitHub repository.

Questions

How do I install Paperdebugger?

Paperdebugger does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/PaperDebugger/paperdebugger.

Are there security reports about Paperdebugger?

No reports found for this package in our research (last checked 2026-10-29). Paperdebugger currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include access to draft files, prompt injection in text, data retention unknown.

Is Paperdebugger actively maintained?

Paperdebugger has 1.6k GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/PaperDebugger/paperdebugger before pinning it in production.

What are alternatives to Paperdebugger?

Notable alternatives to Paperdebugger include Overleaf (Cloud-based LaTeX editor with built-in collaboration and comment features for academic writing), Grammarly (Browser extension and standalone app that checks grammar and style in real-time), Writefull (Editor plugin specifically designed for academic writing feedback and language improvement), Claude or ChatGPT with manual prompts (Use a general AI assistant directly for paper review without a specialized plugin). You can also compare Paperdebugger side by side with other MCP servers in the Related tools section on this page.

README badge and team notes

Maintain or use Paperdebugger? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.

AgentArmorHQ Risk Grade C for Paperdebugger

GitHub README Markdown:

markdown
[![AgentArmorHQ Risk Grade for Paperdebugger](https://agentarmorhq.com/api/badge/paperdebugger-paperdebugger)](https://agentarmorhq.com/skills/paperdebugger-paperdebugger)

HTML embed:

html
<a href="https://agentarmorhq.com/skills/paperdebugger-paperdebugger"><img src="https://agentarmorhq.com/api/badge/paperdebugger-paperdebugger" alt="AgentArmorHQ Risk Grade for Paperdebugger" height="20" /></a>

Terminal check:

terminal
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "paperdebugger-paperdebugger"

Share with your security lead

Need sign-off to use paperdebugger? Copy this note for Slack, a ticket or a pull request.

### AgentArmorHQ Security Review Memo: paperdebugger
- **Listing URL:** https://agentarmorhq.com/skills/paperdebugger-paperdebugger
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.6k GitHub stars

#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** GitHub (PaperDebugger/paperdebugger)

#### Recommended Hardened Setup
- **Source Repo:** https://github.com/PaperDebugger/paperdebugger
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.

_Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type
App connector
Publisher
PaperDebugger
Source code
github.com/PaperDebugger/paperdebugger
Est. context load
~500 tokens / turn (~3 tool schemas, 0.25% of 200k context)
Popularity
1.6k GitHub stars
Last updated
2026-10-29
Last graded
2026-10-22

Community

Discussions for Paperdebugger

Ask questions or share configuration tips. Governed by our Community Rules & Terms.

No posts match this filter yet.

Be the first to ask a question or share a working tip.

Was this listing for Paperdebugger helpful?

Check before you install, in Claude

Your assistant answers Block, Review or No known issues for any package before it installs it.

Get this check inside Claude