PaperDebugger

PaperDebugger is a Chrome extension and multi-agent backend system that integrates with Overleaf to provide AI-assisted academic writing critique, revision suggestions, comment generation, and literature research directly within a LaTeX editing session.

Evaluated Mar 06, 2026 (0d ago) vlatest
Homepage ↗ Repo ↗ Other overleaf latex academic-writing chrome-extension multi-agent ai-writing peer-review citation-verification
⚙ Agent Friendliness
47
/ 100
Can an agent use this?
🔒 Security
70
/ 100
Is it safe for agents?
⚡ Reliability
64
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
0
Documentation
65
Error Messages
55
Auth Simplicity
68
Rate Limits
55

🔒 Security

TLS Enforcement
80
Auth Strength
75
Scope Granularity
60
Dep. Hygiene
70
Secret Handling
65

Community/specialized tool. Apply standard security practices for category. Review documentation for specific security requirements.

⚡ Reliability

Uptime/SLA
70
Version Stability
65
Breaking Changes
60
Error Recovery
60
AF Security Reliability

Best When

A researcher actively writing a paper in Overleaf wants inline AI critique and literature cross-checking without switching to a separate AI chat window.

Avoid When

The team uses offline LaTeX tools, or needs AI that can directly edit and push changes to the document rather than read-only suggestions.

Use Cases

  • Getting AI critique and revision suggestions on a LaTeX paper open in Overleaf without leaving the editor
  • Generating automated reviewer-style comments and inserting them directly into the Overleaf project
  • Running literature research and citation verification agents on paper content
  • Using custom prompt templates for domain-specific academic editing and proofreading

Not For

  • Non-Overleaf LaTeX workflows (offline TeX editors, other platforms)
  • Non-academic writing (business documents, code documentation)
  • Users needing the AI to directly modify or commit changes to the document

Interface

REST API
Yes
GraphQL
No
gRPC
Yes
MCP Server
No
SDK
No
Webhooks
No

Authentication

Methods: jwt oauth
OAuth: Yes Scopes: No

JWT-based authentication with OAuth support. Backend uses Go/Gin with MongoDB. Self-hosted backend URL configurable in extension.

Pricing

Model: open_source
Free tier: Yes
Requires CC: No

AGPL-3.0 license. Underlying OpenAI API costs apply for AI calls. Chrome extension free to install.

Agent Metadata

Pagination
none
Idempotent
Yes
Retry Guidance
Not documented

Known Gotchas

  • No MCP server; AI agents cannot integrate directly without the Chrome extension
  • Requires Chrome browser and Overleaf session; not usable in headless environments
  • Self-hosted backend requires Go 1.24+, MongoDB, and OpenAI API key configuration
  • AGPL-3.0 license has copyleft implications for commercial derivatives

Alternatives

Full Evaluation Report

Detailed scoring breakdown, competitive positioning, security analysis, and improvement recommendations for PaperDebugger.

$99

Scores are editorial opinions as of 2026-03-06.

5173
Packages Evaluated
26151
Need Evaluation
173
Need Re-evaluation
Community Powered