Skip to main content

tex-mcp-web

tests license release python

Review a LaTeX paper from its rendered PDF, on a desktop, tablet, or phone, while Claude Code or Codex edits the source.

A sentence selected in the PDF takes a comment asking for a number. Called, the agent proposes a wording as a −/+ pair, which waits in to do, and the source marks the words it would replace. Applied with aa, it leaves to do empty, and once the paper is compiled, the PDF shows the new sentence.

Select words in the PDF, or draw a box over part of a figure, and write what should change. Press Call agent, the bell above the comments, when they are ready. The agent edits the source, compiles, and answers in the thread, at times with a wording to apply. The keys at the bottom right are the ones pressed.

⭐ If this helps your writing, please give it a star. It helps others find the project.

Quick start

  1. Paste this into Claude Code or Codex, and start the agent again once it is done:

    Install tex-mcp-web by following https://raw.githubusercontent.com/MiiKiyoshi/tex-mcp-web/main/INSTALL.md
    

    The agent checks for Python 3.10 or newer and latexmk, shows where it will install and which agents it will register with, and installs once you agree.

  2. Start the agent in the paper's folder and say do tex init. It finds the main .tex file and a free port, shows you the settings, and writes .tex-mcp-web.yaml once you agree.

  3. Open http://localhost:<port>. On a machine other people log in to, say yes to the page token at do tex init, and open the link tex-mcp-web link prints once in each browser. The agent acts when you press Call agent. With the plugin the install adds, a Claude Code session started in the paper's folder waits for that press by itself. In Codex, or in an older Claude Code that does not support plugin monitors, say do tex listen first, and again after the agent restarts.

Point at what words cannot

On the PDF's second page, the box tool draws a box over a bare table, and the comment asks for rules. Called, the agent rules the table with booktabs and names the lines it changed, the paper compiles, and the PDF shows the ruled table.

For a figure, a table or a page's layout, take the box tool beside pan and pointer in the PDF's toolbar, draw a box over it, and say what is wrong. The agent works from the box as from any comment.

Answer your co-authors' Overleaf comments, with the agent

Press Connect Overleaf in the top bar and paste the project's link. Its comment threads come into a tab of their own, Comments with a leaf, beside the comments you write here. In a thread you talk with the agent, which drafts the reply for Overleaf under it, and you send that reply once it reads right. Each tab opens on to do, what waits for you alone: a suggestion to apply, a reply to send, a suggested edit to accept. The number on the tab counts them, and once it is gone, nothing is left.

A co-author's thread from Overleaf, where the agent misread the request and drafted a gushing reply. A reply to the agent sets it right, and once called, the agent fixes the sentence, the PDF shows it, and the draft for Overleaf becomes one short line, sent with ss.

Your talk with the agent stays on the page, in the thread between your co-authors' messages, so the whole exchange reads in order. Overleaf gets only the replies you send.

The same thread twice. On the review page it holds the co-author's comment, the talk with the agent, each entry of it marked here only, and the reply sent. On Overleaf it holds the comment and the reply sent, and nothing else.

Keeping the paper's files in step with Overleaf, by git, by hand or live, is in Working with Overleaf.

Raise a point with your co-authors on Overleaf

With the leaf beside the comment button pressed, the room temperature is selected in the source with v and gc, and a rough note tells the agent what to ask the co-author. The note waits in the leaf Comments tab under new thread. Called, the agent drafts a polite question, sent with ss: it opens on Overleaf alone, and the note stays on the page, marked here only.

Press the leaf beside + Comment in the editor's bar, select the words in the source, as Overleaf puts a thread on source words, and tell the agent what to say, as roughly as you like. It drafts the thread's first message, worded for your co-authors, and you send it. It opens on Overleaf on those words, and your note stays here. Asked in any thread, the agent drafts a new thread of its own the same way.

Accept or reject your co-authors' suggested edits

The co-author's edits made on Overleaf with track changes on wait in the leaf tab's to do: a word written over another, words put in, words taken out. Each opened with Space shows in the source, underlined or marked where words went. Two are accepted with aa and one rejected with dd, Get takes the rejection into the file, and to do is empty.

Edits your co-authors make on Overleaf with track changes on come in as suggested edits, each a card of what went and what came, and the editor marks them in the source. Accept and Reject, or aa and dd, act on Overleaf for everyone in the project.

Go through the comments by keyboard

All without the mouse: gd into the introduction's file, v and gc to comment on a sentence, Ctrl+Alt+Enter to call the agent, K to its comment, Space and aa to apply its proposal, K back to the words, :make to compile, gss to find the sentence in the PDF, Ctrl+O back to main.tex, and R to resolve.

The comment list goes by keys, as a notebook's cells do, and the editor has Vim keys. A ring marks the comment the keys act on, and the list moves under it, so the eye stays put. K goes between a comment and its words in the source, both ways.

Key Does
j k Next and previous comment
Space Open the comment and show its words
K Into the source at its words, and K there back
r Reply to the agent
R Resolve
aa Apply the suggestion, or accept a suggested edit
ss Send the reply to Overleaf
? Every key

Keys that change the file, post to Overleaf or delete are pressed twice. Once you move by keys, the ringed comment's buttons show their letters. Every key, and the editor's Vim keys, are in Reviewing in detail.

Review on a tablet or phone

The review page at a tablet's width and at a phone's, each on the same comment: the PDF above, zoomed to the commented sentence, and the thread with the agent's proposal below.

The page is served where the agent runs. From a phone, forward its port over SSH from that machine, with Termux on Android or Termius on iOS, then open http://localhost:<port> in the phone's browser:

ssh -L <port>:localhost:<port> <the machine the agent runs on>

In Termius the same forward is a Local rule in its Port Forwarding screen. With the page token on, open the link tex-mcp-web link prints on that machine instead, once.

Writes by your rules, in your field's terms

Rules told to an agent in conversation do not last. After its context is compacted a few times it writes as if never told, and what Claude Code remembers for one paper's folder does not reach the next paper in the same field. Kept in files, your writing rules and your field's terms serve every paper that names them, and in Claude Code the agent cannot use tex-mcp's tools until it has read them, again after every compaction (Codex does not hold the tools back like this yet).

Write the rules you hold a paper to in a GUIDELINE.md, in a folder of its own under ~/.config/tex-mcp-web/guidelines/, and set guideline to the folder's name. A guideline can build on another, so the rules for every paper and those of one field stay apart:

~/.config/tex-mcp-web/guidelines/
├── plain-writing/GUIDELINE.md    rules for every paper
└── my-field/GUIDELINE.md         a field's own, opening with the lines below
---
extends: plain-writing
---

With guideline: my-field, the agent reads plain-writing first and my-field after it.

Left alone, an agent also describes a concept in words of its own where the papers of your field use one term. Convert the papers yours builds on to Markdown with marker, keep them in one folder, and set references to it.

Configuration

do tex init writes .tex-mcp-web.yaml at the paper's root:

main: main.tex
watch:
- '*.tex'
- '*.bib'
ignore:
- '*_backup.tex'
compiler: auto
port: 8765
guideline: my-field
translation:
  language: Korean
  instructions: Keep cell names in English.
overleaf: https://www.overleaf.com/project/0123456789abcdef01234567

Every field is in Configuration.

See also

html-mcp-web reviews an AI agent's HTML slides or report the same way and hands finished slides over as an editable PowerPoint deck.

Acknowledgements

tex-mcp-web is a hard fork of queelius/scholia at commit e6c7454 (version 0.6.1), independently developed since under the MIT license. See LICENSE. PDF viewing uses EmbedPDF and its PDFium WebAssembly engine, whose notices are in tex_mcp_web/static/embedpdf/LICENSE and tex_mcp_web/static/embedpdf/LICENSE.pdfium. The bundled viewer differs from its release only in its zoom gesture, described in Reviewing in detail. Source highlighting and completion use Ace Editor builds 1.44.0 under the BSD-3-Clause license, and its notice is in tex_mcp_web/static/ace/LICENSE.

Metadata

Release files for tex-mcp-web 0.8.4

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for tex-mcp-web 0.8.4
File Size Uploaded Provenance Actions
tex_mcp_web-0.8.4.tar.gz 3.1 MB With provenance Details for tex_mcp_web-0.8.4.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for tex-mcp-web 0.8.4
File Interpreter ABI Platform Actions
tex_mcp_web-0.8.4-py3-none-any.whl Python 3 none any Details for tex_mcp_web-0.8.4-py3-none-any.whl

Total release size: 6.0 MB

Release files / tex_mcp_web-0.8.4.tar.gz

Download URL tex_mcp_web-0.8.4.tar.gz
Size 3.1 MB
Tags Source
SHA-256 checksum
How to use checksums
a38b23bdcf27b1c0305c1964b2714048787b096cd6937405e5797be279da1bf7
BLAKE2b-256 checksum
How to use checksums
55b7e7a08fe6d8b44ad4b10cde39383aa493b84869b7a6c69c3219da9d01a30c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 13, 2026.

Transparency log

Release files / tex_mcp_web-0.8.4-py3-none-any.whl

Download URL tex_mcp_web-0.8.4-py3-none-any.whl
Size 2.9 MB
Tags Python 3
SHA-256 checksum
How to use checksums
55274b2b9debf99a50efabaefc0fce868dc8ecd4c1389d59d466c270c29ba20f
BLAKE2b-256 checksum
How to use checksums
867ee6b9a5e74a1f094363cf91cdab355cb08791064fa980af39a075ed91b5a7
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 13, 2026.

Transparency log

Security for tex-mcp-web 0.8.4

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for tex_mcp_web-0.8.4.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 13, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page