paperdebugger
Verified Safeby PaperDebugger
Overview
An AI-powered academic writing assistant integrated with Overleaf for debugging and improving LaTeX papers through intelligent suggestions, critique, and revision.
Installation
make build && ./dist/pd.exeEnvironment Variables
- OPENAI_API_KEY
- MCP_BASIC_KEY
- MCP_PAPERSCORE_KEY
- XTRAGPT_OPENAI_API_KEY
- XTRAGPT_OPENREVIEW_BASE_URL
- XTRAGPT_OPENREVIEW_USERNAME
- XTRAGPT_OPENREVIEW_PASSWORD
- GHCR_DOCKER_CONFIG
- CLOUDFLARE_TUNNEL_TOKEN
- MONGO_URI
- PAPERDEBUGGER_IMAGE
- PD_API_ENDPOINT
- PD_GA_TRACKING_ID
- PD_GA_API_SECRET
- SAFARI_BUILD
- MONOREPO_REVISION
- BETA_BUILD
- VERSION
Security Notes
The system interacts with Overleaf using session cookies (overleaf_session2, GCLB) and CSRF tokens via WebSocket, which requires careful handling to prevent session hijacking. Client-side OAuth client IDs are hardcoded, though these are often public. Environment variables for API keys use dummy defaults for local development, which should not be used in production. The XtraMCP backend, critical for advanced features, is currently closed-source, posing a black box in terms of its security. The project acknowledges the need for HTTPS for custom backend endpoints, indicating security awareness for network communication. No direct 'eval' or obvious malicious patterns were found.
Similar Servers
deep-research
An AI-powered research assistant that generates comprehensive reports, leverages various LLMs and web search engines, and offers integration as a SaaS or MCP service.
zotero-mcp
Integrates Zotero, a leading reference management tool, with AI assistants through the Model Context Protocol (MCP) to enable intelligent search, retrieval, and analysis of academic literature and annotations.
code-assistant
An AI coding assistant that integrates with code editors to provide autonomous code analysis and modification, supporting multiple UI modes and the Agent Client Protocol (ACP).
academia_mcp
Provides a server for searching, fetching, analyzing, and reporting on scientific papers and datasets using various APIs and optional LLM-powered tools.