paperassist
Provides LaTeX writing task packs and import validation for drafting, reviewing, and repairing manuscripts, including draft.tex handling and a latex-fix skill.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
PaperAssist
PaperAssist is a model-free research runtime and an OpenClaude / Claude Code plugin. It plans research, defines controlled experiments, prepares LaTeX writing tasks, reviews manuscripts and verifies releases — while the only language model is the AI harness you already run. PaperAssist ships no provider client, no API key handling and no model selection.
⚠️ Disclaimer: this project is for learning and research. Do not use it commercially. You are responsible for anything you produce with it.
Contents
Related MCP server: FronyBoard
What changed in v4
Area | v3 | v4 |
Language model | Bundled OpenAI-compatible client, provider registry, credentials | None. The AI harness is the executor ( |
Generation | In-process agent runtime called the model | Deterministic task packs the harness executes |
Integration | Custom CLI only | OpenClaude plugin with skills and an MCP server |
Runtime |
| Pack → harness → import gate is the runtime |
Package |
|
|
How it works
flowchart LR
U["Researcher / agent"] --> S["OpenClaude skill / MCP tool"]
S --> P["Task pack<br/>plan.json + tasks + agent-brief.md"]
P --> H["AI harness<br/>(OpenClaude, Claude Code)"]
H --> R["Result file<br/>ideas.json / review.json / experiment.json / draft.tex"]
R --> G["Import gate<br/>deterministic validation"]
G --> A["Artifacts + SQLite memory"]PaperAssist never generates text. It owns:
Planning: packs, task lists, briefs, acceptance rules.
Binding: protected experiment blocks, citations.
Verification: citation keys, score ranges, artifact hashes, release gates.
Install as OpenClaude plugin
Tambahkan ke direktori plugin user OpenClaude:
cp -r . /c/Users/<you>/.openclaude/plugins/paper-assistAtau clone langsung:
git clone https://github.com/mahdyarief/paper-assist.git ~/.openclaude/plugins/paper-assistLalu aktifkan:
cd ~/.openclaude/plugins/paper-assist
python -m pip install -r requirements-core.txtVerifikasi MCP server:
python mcp_servers/stdio.pyUsing the plugin
Plugin ini dideklarasikan oleh .claude-plugin/plugin.json. Skill dibaca
dari skills/, dan MCP server paperassist berada di
mcp_servers/stdio.py (JSON-RPC over stdio).
MCP tools (10):
Group | Tools |
|
|
|
|
Writing a paper: AI Harness → Paper-Assist
PaperAssist bukan generator teks. Alurnya:
Harness memanggil
pack_scaffold(ideation / experiment / review / writing).Harness membaca
plan.json+agent-brief.md+tasks/*.jsondari pack.Harness melakukan pekerjaan (ide, uji, review, draft LaTeX).
Hasil diimpor kembali lewat
pack_import/writing_import— gate deterministik dijalankan sebelum catatan disimpan ke SQLite dan.paperassist/.
Contoh (dari harness/agent, bukan konsol CLI):
# 1. Scaffold pack ideation
pack_scaffold { "workspace": "<ws>", "kind": "ideation", "topic": "...", "venue": "NeurIPS" }
# 2. Harness kerjakan task dari pack, lalu impor hasil
pack_import { "workspace": "<ws>", "run_id": "<id>", "import": "ideas.json" }
# 3. Writing pack untuk draft LaTeX
writing_pack { "workspace": "<ws>", "topic": "...", "title": "..." }
writing_import { "workspace": "<ws>", "run_id": "<id>", "import": "draft.tex" }Catatan: tool
pack_scaffold,pack_task,pack_import,writing_pack,writing_import, dst. dipanggil assistant (OpenClaude / Claude Code) melalui MCP serverpaperassistyang sudah aktif sebagai plugin.
Skills included
Skill | Purpose |
| Draft one section without taking over the pipeline |
| Tighten logic/wording/structure in one section |
| Find the single most important missing citation |
| Pick references that best fit the manuscript |
| Remove templated AI tone without changing the argument |
| Apply one local LaTeX repair round |
Workspace layout
<workspace>/
├── .paperassist/
│ ├── paperassist.db # workflows, claims, evidence, artifacts
│ ├── packs/<kind>/<run-id>/ # plan.json, agent-brief.md, tasks/, target
│ ├── ideation/<run-id>/ # validated ideas.json
│ ├── experiments/<run-id>/ # validated result.json
│ ├── review/<run-id>/ # validated review.json
│ ├── publication/
│ └── release_manifest.json
├── artifacts/
├── main.tex
└── references.bibScientific integrity
No invented metrics, datasets, baselines, hardware or citations.
Every quantitative claim must trace to a run, artifact or bibliography entry.
Protected experiment blocks are author-owned and byte-preserved.
Secrets are rejected at input, never written into a workspace.
License
MIT. See LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Project management shared by people and AI agents, with persistent project state through MCP.
Project management MCP for AI agents with safe task reads and writes.
Task management your AI agents can actually run. One line becomes a context-ready task over MCP.
AI workflow/MCP implementation package planner.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI-assisted scientific research workflow management through MCP, including project creation, ideation, experiment execution, and artifact handling, with integration for ChatGPT, Codex, and Claude Code.Apache 2.0
- AlicenseAqualityBmaintenanceEnables AI agents to manage projects, roadmaps, periods, and tasks through MCP tools, backed by a local SQLite database with schema validation.20MIT
- FlicenseBqualityBmaintenanceEnables deterministic, harness-neutral research workflows by unifying research object identity, evidence receipts, claim-evidence graphs, and append-only decision logs, along with specialized scholarly skills for literature analysis, reproducibility audits, and multi-agent review.18660 PyPI1-
- AlicenseAqualityBmaintenanceEnables AI agents and MCP clients to run research as an explicit scientific process: forming hypotheses, designing and executing sealed experiments, capturing observations and artifacts, linking claims to supporting evidence, and reviewing provenance. Exposes coordinated MCP services so users can inspect, reproduce, and audit every step from question to conclusion rather than trusting an opaque final answer.4621Apache 2.0