mcpField
R
refereekit

refereekit

Local
inferweave.comScience & Education0Updated 2w ago
RepositoryVisit website

About refereekit

refereekit supports confidential, human-led peer review by checking citations in a paper against its submitted PDF, then drafting a referee report and editor letter. It is intended for researchers who want to verify evidence while keeping the verdict and edits in human hands.

Key features

  1. 01Check quotations, pages, equations, and figures
  2. 02Draft a referee report and editor letter
  3. 03Match drafts to a reviewer's style
  4. 04Keep the paper out of the agent model

Use cases

  1. 01Verify citations in a submitted manuscript
  2. 02Prepare a report from checked claims
  3. 03Practice a review with the tutorial

MCP support

The README describes setup for use with pi, Claude Code, Codex, Claude Desktop, and a ChatGPT desktop preview, but does not specify an MCP interface.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "com-inferweave-refereekit": {
      "command": "uvx",
      "args": [
        "refereekit"
      ]
    }
  }
}
Run commanduvx refereekit

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypirefereekit1.0.2

Tools

8

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
pdfstringYesPath of the PDF, as the referee gave it
venuestringNoOptional venue ID the referee named, without spaces
sessionstringNoA session reference such as s-0123abcd, from refx_start or refx_status

Details

From the project README

refereekit

refereekit helps you referee a paper with a language model. It checks every quotation, page, equation and figure that an answer or a draft cites against the submitted PDF. It then drafts a referee report and an editor letter in your style, from claims that checked out. You edit them. The verdict is yours.

You need a terminal and uv. Two commands start a review:

uv tool install refereekit
refx chat paper.pdf

In the chat, /model access sets your model. For anthropic, bedrock and vertex it names one more install line. /tutorial runs a practice review that needs no key. Your terminal is the private view.

You can also review in pi, Claude Code, Codex or Claude Desktop, or in the ChatGPT desktop app as a preview. Paste the setup prompt into your agent, which sets refereekit up. refereekit never gives the paper to the agent's model. What you type in the agent's chat does reach it, so keep the paper's title out. You read the paper, and type your judgment, in a private view.

Confidentiality first. A manuscript under review goes only to a model backend, after you attest what its account keeps. It never enters this repository. See Confidentiality.

Documentation: start with Before you start, then pick a reading path from the documentation index.

Citation

If you use refereekit in your research, please cite the following paper:

@inproceedings{yen2026models,
    title={Models Quote, Code Verifies, Humans Judge: Lessons for AI-Assisted Peer Review},
    author={Tzu-Chi Yen},
    booktitle={NeurIPS 2026 Workshop on AI-Native Academia},
    year={2026}
}

License

MIT. See LICENSE.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.