- Research Hub @wenyuchiou/research-hubResearch workspace for Zotero + Obsidian + NotebookLM. Search, ingest, sync, verify briefs.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.64 GitHub stars.
- Overleaf @younesbensafia/overleaf-mcp-serverMCP server for managing Overleaf projects through Git synchronization.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.62 GitHub stars.
- paper-preflight @amos689/paper-preflightChecks every LaTeX reference against Crossref, dblp, arXiv, DataCite, PubMed and OpenAlex. No LLM.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.35 GitHub stars.
- AIRAS @airas-org/airasAutomated AI research toolkit: hypothesis generation, experiments, and paper writing6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.35 GitHub stars.
- Scholar Sidekick @mlava/scholar-sidekick-mcpCatch AI-fabricated citations (real DOI + fake title). Retraction, open-access, 10,000+ CSL styles.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.11 GitHub stars.
- MagicTeX @zoelinuts/magictexLaTeX editor for AI agents: live PDF preview, PDF comments that drive edits, git history3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- LaTeX @sepinetam/latex-mcpEnable AI agents to compile TeX files with LaTeX inside a Docker container.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- OokCite @turtletech-ehf/ookcite-mcpCatch fabricated citations: verify DOIs/ISBNs and format them in 2900+ CSL styles.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- MiLatexAI @yasaminfayyaz/milatexaiEdit your Overleaf LaTeX projects from Claude and ChatGPT; every change is a real Git commit.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.2 GitHub stars.
- Latex Submission Lint @jmshinhwa/latex-submission-lintSeventeen rules on your .tex file: the statements the editorial office looks for, and the source tha5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Academic Research Kernel @xngg1021/academic-research-kernelDeterministic research state, evidence validation and statistical recomputation.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- CiteVahti @heidihelena/citevahtiChecks whether each cited source supports the claim it backs. Blinded human-first, local-first.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Citeguard @xiaweiyi713/citeguardFalsification-first citation auditor: existence, metadata, and claim-support checks via MCP.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Openpaper @federicodeponte/openpaper-mcpAutonomous research engine: auto research from a prompt to a fully-cited academic paper via MCP6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Sourceright @edithatogo/sourcerightReference verification MCP server for CSL bibliographies, evidence, and audited writes.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- Overleaf @yangzichao/mcp-server-overleafOverleaf MCP server for Claude, Codex, ChatGPT, and Cursor with safe LaTeX editing and review.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Papers @agentpub/papersSubmit papers for AI peer review and publication. Search and cite AI-authored research.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- MLA Citation Generator MCP @rocnubie/mla-citation-generator-mcpMLA Citation Generator creates accurate MLA-format citations from a DOI, ISBN, URL, or manual4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Publish.fun @publish/mcpAI-native research journal: submit papers for AI peer review, track decisions, revise, and cite.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- refcheck @benchoi93/refcheckVerify academic citations against real databases. Catches hallucinated references, exports BibTeX.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- LetX @letx/letxCollaborative LaTeX editor: search 1000+ templates, edit projects, and compile them to PDF.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
Academic writing MCP servers
A server here writes academic papers: LaTeX, citations, journal formatting.
Not here: finding papers to read.
19 remote32 localTagged by Odel's AI, which can make mistakes
Most popular in Academic writing
By GitHub stars, at most two per publisher- Number 1: Bibverify@hylouis233/bibverifyVerify and repair BibTeX references with DOI-first MCP tools.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.99 GitHub stars.
- Number 2: Paper Format Agent@zxyasfas/paper-format-agentLocal-first DOCX formatter for academic papers with a content-fingerprint integrity guard.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.81 GitHub stars.
- Number 3: OneCite@hzacode/oneciteGenerate academic citations from DOI, arXiv, titles, or URLs in BibTeX, APA, MLA formats.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.67 GitHub stars.
