convez.ai
MCP ServerBusca & PesquisaIntermediário
JhonHander

Academic Agent Toolkit

JhonHander/academic-agent-toolkit

Configure ferramentas de pesquisa acadêmica em todos seus agentes de IA

Ver no GitHub
InicialPluginScore · de 0 a 100

MCP server que instala habilidades de pesquisa acadêmica e busca de papers em múltiplos agentes de IA (Claude, Cursor, Copilot) com uma única linha de comando. Inclui suíte de pesquisa profunda, revisão de literatura, redação de artigos, planejamento de experimentos e acesso a 20+ bases acadêmicas.

Instalação

$npx convez-ai JhonHander/academic-agent-toolkit

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
9
Forks
0
Acompanhando
0
Saúde
42%
Último commit
há 5 meses
Versão
v0.1.3
Issues abertas
0
Contribuidores
1

Casos de uso

  • Revisão sistemática de literatura para dissertações e teses
  • Busca integrada em arXiv, PubMed, Semantic Scholar e Crossref
  • Planejamento de protocolos de pesquisa e validação de reprodutibilidade

Veredito

Ferramenta completa e bem pensada para pesquisadores acadêmicos. A abordagem unificada de configuração cross-agent resolve um problema real, mas exige Python 3.11+ e familiaridade com CLI — adequado para usuários técnicos em contexto acadêmico.

README

A tradução para o português deste README ainda está na fila.

Academic Agent Toolkit (AAT)

One command to install academic research skills and paper search across all your AI coding agents.

Students and researchers use different AI agents (Claude Code, OpenCode, Cursor, Copilot, Codex). Each agent needs different config formats, different file locations, and different skill setups. AAT handles all of that so you can focus on your research.


What you get

ComponentWhat it does
Academic Research SuiteDeep research, lit reviews, systematic reviews, paper drafting, peer review, experiment planning
Experiment AgentStudy protocol design, statistical interpretation, reproducibility validation
Paper Search MCPSearch 20+ academic sources (arXiv, PubMed, Semantic Scholar, Crossref...) and download PDFs

All configured across every supported agent in one command. No manual JSON/TOML editing.


Installation

Prerequisites: Python 3.11+ and uv.

If you are not a Python developer, use the uvx option. It runs the latest published version from PyPI without making you manage a virtual environment.

Pick one:

# Recommended: run directly from PyPI, no permanent install
uvx academic-agent-toolkit doctor

# Persistent install: keeps the `aat` command available in your terminal
uv tool install academic-agent-toolkit
aat doctor

# Standard pip install
pip install academic-agent-toolkit
aat doctor

After install, run:

aat install
aat setup-keys
aat verify

Quick Start

aat doctor      # See what agents are detected
aat install     # Install everything (skills + MCP)
aat setup-keys  # Configure API keys interactively
aat verify      # Confirm everything works

How it works

New users — aat install downloads Academic Research Suite and Experiment Agent automatically, creates a private .env file for your API keys, installs one canonical skill in ~/.agents/skills/academic-research-suite, and configures Paper Search MCP in every detected agent.

Existing users — AAT adopts your existing ARS installation and Paper Search MCP registrations. It skips what you already have and only manages what's missing. Use --replace-skills or --replace-mcp if you want AAT to take over an existing setup.

The .agents/ layout is the source of truth. Agents with native skill directories get symlinks to the canonical .agents skill instead of duplicated copies.


Commands

CommandWhat it does
aat doctorShow environment readiness and agent detection
aat installInstall skill adapters and MCP configs with a guided plan
aat setup-keysConfigure Paper Search MCP API keys interactively
aat verifyConfirm everything is in place
aat self-checkValidate runtime prerequisites (Python, uv, ARS source, env file)
aat repairRe-apply the last saved installation
aat updateCheck PyPI, upgrade AAT, then re-apply the saved installation
aat uninstallRemove AAT-managed files safely (does not touch your own configs)

API Keys

Paper Search MCP works without most keys, but some sources need credentials. AAT helps you set them up interactively with aat setup-keys.

VariableRequired?Recommended?Where to get it
PAPER_SEARCH_MCP_UNPAYWALL_EMAILyes—unpaywall.org
PAPER_SEARCH_MCP_CORE_API_KEYnoyescore.ac.uk
PAPER_SEARCH_MCP_SEMANTIC_SCHOLAR_API_KEYnoyessemanticscholar.org
PAPER_SEARCH_MCP_GOOGLE_SCHOLAR_PROXY_URLnonoYour proxy provider
PAPER_SEARCH_MCP_DOAJ_API_KEYnonodoaj.org
PAPER_SEARCH_MCP_ZENODO_ACCESS_TOKENnonozenodo.org
PAPER_SEARCH_MCP_IEEE_API_KEYnonodeveloper.ieee.org
PAPER_SEARCH_MCP_ACM_API_KEYnonoacm.org

Keys are stored in a single private file (~/.config/paper-search-mcp/.env by default). Paper Search MCP reads them automatically via PAPER_SEARCH_MCP_ENV_FILE. No keys are duplicated across agent configs.


Supported Agents

Skill adapters (agent-optimized routers for Academic Research Suite):

  • Zed (~/.agents/skills/ native global skill)
  • Claude Code
  • OpenCode
  • Cursor
  • GitHub Copilot (~/.agents/skills/ and ~/.copilot/skills/ global skills)
  • Codex

GitHub Copilot loads skills from ~/.agents/skills/ and ~/.copilot/skills/ globally, and from .github/skills/, .claude/skills/, and .agents/skills/ per project. AAT already installs the canonical skill to ~/.agents/skills/ and symlinks to ~/.copilot/skills/, so Copilot picks it up automatically. VS Code does not expose a global skills directory — it is configured for MCP only.

MCP configuration (Paper Search MCP registration):

  • Claude Code
  • OpenCode
  • Cursor
  • Codex
  • VS Code (user and global)
  • GitHub Copilot
  • Zed

See docs/mcp-agent-matrix.md for the exact config format used per agent.


Install flags

FlagPurpose
--no-bootstrapSkip automatic ARS download; requires an existing source
--ars-source PATHUse a specific ARS source tree
--env-file PATHUse a custom .env file path
--replace-skillsBack up and replace existing skill directories
--replace-mcpBack up and replace existing MCP entries
--dry-run --yesPreview the full plan without writing files

Uninstall

aat uninstall

Removes only files AAT created. Your existing hand-written configs and skill directories are never touched. Optional flags:

  • --remove-env also removes the Paper Search MCP env file
  • --remove-managed-ars also removes AAT's downloaded ARS source

Where files live

WhatLocation
AAT config~/.config/academic-agent-toolkit/config.json
Canonical global skill~/.agents/skills/academic-research-suite/
Zed global agent instructions block~/.agents/AGENTS.md
Managed ARS source~/.local/share/academic-agent-toolkit/ars/
Paper Search MCP env~/.config/paper-search-mcp/.env (default)
Skill symlinks~/.claude/skills/, ~/.config/opencode/skills/, ~/.cursor/skills/, ~/.codex/skills/

Upstream projects

AAT is an integration layer. It bundles and configures these upstream projects with their permission:


Developer testing

Use two separate environments when developing AAT:

EnvironmentPurposeCommand source
Local / sandboxTest your current code before publishingThis checkout on your machine
ProductionTest what real users get from PyPIPublished academic-agent-toolkit package

Local sandbox

From the repository root:

# Run the CLI from your local source tree
uv run aat doctor
uv run aat install --dry-run --yes
uv run aat verify

Use this before publishing. It tests the code you are editing locally, even if it is not on PyPI yet.

Production check from PyPI

Use this after publishing a release:

# Run the latest published version from PyPI
uvx academic-agent-toolkit doctor

# Or install it persistently like a real user would
uv tool install --force academic-agent-toolkit
aat doctor
aat install --dry-run --yes
aat verify

Use this to confirm that PyPI users receive the expected version and behavior.


License

MIT — see LICENSE.

Ver o original no GitHub

Bom para

Relacionados