DEV.co
MCP Servers · PaperDebugger

paperdebugger

PaperDebugger is a Chrome extension that integrates AI-powered writing assistance directly into Overleaf, helping researchers improve academic papers through intelligent suggestions, critique, and revision workflows. It uses a custom multi-agent orchestration engine (XtraMCP) to simulate research, critique, and revision cycles without modifying the original document.

Source: GitHub — github.com/PaperDebugger/paperdebugger
1.5k
GitHub stars
71
Forks
TypeScript
Primary language
AGPL-3.0
License (OSI-approved)

Key facts

Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.

FieldValue
RepositoryPaperDebugger/paperdebugger
OwnerPaperDebugger
Primary languageTypeScript
LicenseAGPL-3.0 — OSI-approved
Stars1.5k
Forks71
Open issues15
Latest releasev2.12.28 (2026-01-12)
Last updated2026-07-03
Sourcehttps://github.com/PaperDebugger/paperdebugger

What paperdebugger is

TypeScript-based browser extension with Go 1.24+ backend (Gin/gRPC microservices), MongoDB persistence, and OpenAI API integration. Features JWT/OAuth authentication, custom MCP orchestration engine, and Protocol Buffer APIs for structured multi-step reasoning workflows in academic writing contexts.

Quickstart

Get the paperdebugger source

Clone the repository and explore it locally.

terminalbash
git clone https://github.com/PaperDebugger/paperdebugger.gitcd paperdebugger# follow the project's README for install & configuration

Need it deployed, integrated, or customized instead? DEV.co ships production installs.

Best use cases

Overleaf-integrated manuscript review and iteration

Teams writing LaTeX papers in Overleaf can request AI-assisted critique, suggestions, and targeted revisions without context switching. The comment system and one-click insertion streamline collaborative feedback loops.

Structured multi-step academic reasoning

Researchers needing domain-specific critique (conference reviews, citation verification, literature grounding) can leverage the XtraMCP orchestration to simulate reviewer-style feedback and structured revision passes beyond chat.

Self-hosted writing assistance for privacy-sensitive research

Organizations requiring on-premise deployment can self-host the backend and configure custom endpoints, keeping sensitive manuscript content local while retaining AI-assisted workflow integration.

Implementation considerations

  • Backend self-hosting requires Go 1.24+, MongoDB, and OpenAI API credentials; development setup documented in DEVELOPMENT.md but production hardening steps not detailed in excerpt.
  • Chrome extension dependency limits reach to Chrome-based browsers; Firefox, Safari, or mobile workflows require separate tooling.
  • XtraMCP orchestration engine (referenced in docs/xtramcp/readme.md) is custom and not yet widely tested in production; verify performance and failure modes in your domain before large-scale adoption.
  • JWT/OAuth authentication assumes Overleaf or self-hosted identity provider integration; non-standard auth schemes may require custom backend modification.
  • Data isolation: extension reads LaTeX content; verify logging, caching, and API call handling meet your institutional data governance policies.

When to avoid it — and what to weigh

  • Need non-LaTeX document support — PaperDebugger is purpose-built for Overleaf/LaTeX. Google Docs, Word, or plaintext workflows are not supported; consider alternatives like Grammarly or native LLM plugins.
  • Require strong production SLA or enterprise support — README indicates the team is actively working to improve 'long-term reliability' and notes they are 'hoping to iron out issues this month.' Production-critical workflows should verify stability and support terms first.
  • Cannot accept AGPL-3.0 licensing obligations — The project is licensed under AGPL-3.0, which requires derivative works and network-distributed versions to be open-source. Proprietary or closed-source modifications trigger copyleft obligations; requires legal review for commercial integration.
  • Heavy reliance on offline or air-gapped environments — The system requires OpenAI API calls and backend connectivity. Fully offline operation or restrictive network policies will block core functionality.

License & commercial use

AGPL-3.0 (GNU Affero General Public License v3.0). This is a copyleft license requiring that any derivative work, modification, or network-distributed version must also be open-source under AGPL-3.0 and provide source code to users upon request. Purely internal use (self-hosted) on private networks is permitted; public-facing services or redistributed binaries trigger disclosure obligations.

Commercial use of the unmodified software as-is (via the Chrome Web Store) appears permissible as a user. However, any proprietary modifications, custom backend integrations, or resale of derived versions triggers AGPL-3.0 copyleft obligations—source code must be made available to users and licensees under the same terms. Requires legal review before integrating into commercial products or services. No proprietary commercial license noted in the repository.

DEV.co evaluation signals

Editorial assessment — not user reviews. Directional, with an explicit confidence level.

SignalAssessment
MaintenanceActive
DocumentationAdequate
License clarityClear
Deployment complexityModerate
DEV.co fitGood
Assessment confidenceMedium
Security considerations

Extension reads LaTeX content from Overleaf and sends it to backend for AI processing; data residency and retention policies not disclosed. JWT/OAuth authentication is in place, but no mention of encryption in transit, input validation rules, or audit logging. Self-hosted deployments inherit their operator's security posture. No public security policy, responsible disclosure process, or third-party audit record referenced. Treat as emerging tooling; conduct security assessment before handling sensitive research or confidential manuscripts.

Alternatives to consider

Overleaf native AI features or ChatGPT plugins

Overleaf may add built-in AI writing tools; ChatGPT's web plugin ecosystem avoids extension installation and AGPL licensing but lacks LaTeX-specific orchestration.

Grammarly or ProWritingAid

Established writing assistants with broader document format support, stronger SLAs, and simpler licensing, though less suited to academic multi-step reasoning workflows.

Custom internal LLM integration (Claude API, Llama fine-tuning)

Full control over model, data, and licensing, but requires engineering effort to build Overleaf-specific UI and MCP-style orchestration; no turnkey product.

Software development agency

Build on paperdebugger with DEV.co software developers

Start with the Chrome Web Store extension for a quick trial, or contact us to plan a self-hosted backend deployment for your organization's privacy and compliance needs.

Talk to DEV.co

Related open-source tools

Surfaced by semantic similarity across the DEV.co open-source index.

Related on DEV.co

Explore the category and the services that help you build with it.

paperdebugger FAQ

Does PaperDebugger modify my Overleaf document?
No. PaperDebugger only reads your LaTeX content and provides suggestions. Insertion of AI responses is user-initiated via one-click buttons; your document is never auto-modified.
Can I use PaperDebugger without OpenAI?
Not with the default backend. The system integrates with OpenAI API. Self-hosted deployments could theoretically support alternative LLM providers via backend modification, but this is not documented or officially supported.
What does AGPL-3.0 mean for my company if we want to use PaperDebugger?
Using the unmodified Chrome extension is fine. If you modify, redistribute, or integrate it into a service you offer to others, you must publish your source code under AGPL-3.0 and provide it to users. Consult legal counsel before commercial integration.
How stable is PaperDebugger for production use?
The team is actively fixing reliability issues (per README). No SLA or stability guarantees are published. Test thoroughly in your workflow before deploying to mission-critical research pipelines; monitor Discord/community channels for updates.

Software developers & web developers for hire

From first prototype to production, DEV.co delivers software development services around tools like paperdebugger. Our software development agency staffs experienced software developers and web developers for custom software development, web development, integrations, and ongoing support across mcp servers and beyond.

Ready to Deploy PaperDebugger?

Start with the Chrome Web Store extension for a quick trial, or contact us to plan a self-hosted backend deployment for your organization's privacy and compliance needs.