Skip to main content

Plug-and-play CLI for academic research agent skills and Paper Search MCP setup

Project description

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

Component What it does
Academic Research Suite Deep research, lit reviews, systematic reviews, paper drafting, peer review, experiment planning
Experiment Agent Study protocol design, statistical interpretation, reproducibility validation
Paper Search MCP Search 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.


Quick Start

Prerequisites: Python 3.11+, uv.

# See what agents are detected and what's missing
uvx academic-agent-toolkit doctor

# Install everything (skills + MCP) with one guided command
uvx academic-agent-toolkit install

# Configure your API keys interactively
uvx academic-agent-toolkit setup-keys

# Verify the installation
uvx academic-agent-toolkit verify

The shorthand aat works everywhere:

uvx aat doctor
uvx aat install
uvx aat setup-keys
uvx aat verify

How it works

New usersaat install downloads Academic Research Suite and Experiment Agent automatically, creates a private .env file for your API keys, 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.


Commands

Command What it does
aat doctor Show environment readiness and agent detection
aat install Install skill adapters and MCP configs with a guided plan
aat setup-keys Configure Paper Search MCP API keys interactively
aat verify Confirm everything is in place
aat self-check Validate runtime prerequisites (Python, uv, ARS source, env file)
aat repair Re-apply the last saved installation
aat uninstall Remove 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.

Variable Required? Recommended? Where to get it
PAPER_SEARCH_MCP_UNPAYWALL_EMAIL yes unpaywall.org
PAPER_SEARCH_MCP_CORE_API_KEY no yes core.ac.uk
PAPER_SEARCH_MCP_SEMANTIC_SCHOLAR_API_KEY no yes semanticscholar.org
PAPER_SEARCH_MCP_GOOGLE_SCHOLAR_PROXY_URL no no Your proxy provider
PAPER_SEARCH_MCP_DOAJ_API_KEY no no doaj.org
PAPER_SEARCH_MCP_ZENODO_ACCESS_TOKEN no no zenodo.org
PAPER_SEARCH_MCP_IEEE_API_KEY no no developer.ieee.org
PAPER_SEARCH_MCP_ACM_API_KEY no no acm.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):

  • Claude Code
  • OpenCode
  • Cursor
  • GitHub Copilot
  • Codex (opt-in with --include-codex)

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

Flag Purpose
--no-bootstrap Skip automatic ARS download; requires an existing source
--ars-source PATH Use a specific ARS source tree
--env-file PATH Use a custom .env file path
--replace-skills Back up and replace existing skill directories
--replace-mcp Back up and replace existing MCP entries
--include-codex Also install the Codex skill adapter
--dry-run --yes Preview 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

What Location
AAT config ~/.config/academic-agent-toolkit/config.json
Managed ARS source ~/.local/share/academic-agent-toolkit/ars/
Paper Search MCP env ~/.config/paper-search-mcp/.env (default)
Skill adapters ~/.claude/skills/, ~/.config/opencode/skills/, ~/.cursor/skills/, ~/.copilot/skills/

Upstream projects

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


License

MIT — see LICENSE.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

academic_agent_toolkit-0.1.0.tar.gz (2.1 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

academic_agent_toolkit-0.1.0-py3-none-any.whl (21.0 kB view details)

Uploaded Python 3

File details

Details for the file academic_agent_toolkit-0.1.0.tar.gz.

File metadata

  • Download URL: academic_agent_toolkit-0.1.0.tar.gz
  • Upload date:
  • Size: 2.1 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.26 {"installer":{"name":"uv","version":"0.9.26","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Zorin OS","version":"18","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for academic_agent_toolkit-0.1.0.tar.gz
Algorithm Hash digest
SHA256 c4f5a4829f0a22793ef567d1d67721d7488ae3726fe55e043ee828665edfa4c6
MD5 d2761da774f0265b53e87135d5815305
BLAKE2b-256 f5ce772528e12d3b3c1cd9c489b55c30b997616f5815d341957a0360a56bd94b

See more details on using hashes here.

File details

Details for the file academic_agent_toolkit-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: academic_agent_toolkit-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 21.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.26 {"installer":{"name":"uv","version":"0.9.26","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Zorin OS","version":"18","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for academic_agent_toolkit-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 7ed5d64ba0e1df3fc7a975d8301e85b097a0f42fbd83d258ed69853716c129b3
MD5 4d1674c98948d2da962deb157429f896
BLAKE2b-256 a0eb9ad614ababb4feb40590f8355ead42a3c96fd3a48fc375d0662b3af7a6c2

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page