# refereekit (pypi · refereekit)

Confidential peer review that checks a paper's citations. Set up from the install page first.

- Trust score: 66/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- pypi · `refereekit`: 66/100 (this document), [markdown](https://verifymcp.io/servers/com-inferweave-refereekit/refereekit.md), [page](https://verifymcp.io/servers/com-inferweave-refereekit/refereekit)

## Channel facts

- Registry: `pypi`
- Package: `refereekit`
- Version: `1.0.2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - 2 of 14 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 5 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 61/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1749 tokens (~218/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "refx_close" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the refereekit MCP server?

refereekit runs locally as a PyPI package, launched with uvx refereekit mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add com-inferweave-refereekit -- uvx refereekit mcp
```

### Cursor

```json
{
  "mcpServers": {
    "com-inferweave-refereekit": {
      "command": "uvx",
      "args": [
        "refereekit",
        "mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-inferweave-refereekit": {
      "command": "uvx",
      "args": [
        "refereekit",
        "mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add com-inferweave-refereekit -- uvx refereekit mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-inferweave-refereekit": {
      "type": "local",
      "command": [
        "uvx",
        "refereekit",
        "mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-inferweave-refereekit --command uvx --arg refereekit --arg mcp
```

### Hermes

```yaml
mcp_servers:
  com-inferweave-refereekit:
    command: "uvx"
    args: ["refereekit", "mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "com-inferweave-refereekit": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "refereekit",
        "mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-inferweave-refereekit -t stdio -c uvx -a refereekit mcp
```

### Other

```json
{
  "mcpServers": {
    "com-inferweave-refereekit": {
      "command": "uvx",
      "args": [
        "refereekit",
        "mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 66, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-31 (score 51)

First indexed and scored.

## MCP tools (8)

### `refx_start` (~99 tokens)

refereekit: start

Start a refereekit session on a PDF the referee named, or resume one. Returns the session reference and page count, never the paper's text.

Input parameters:

- `pdf` (string, required): Path of the PDF, as the referee gave it
- `session` (string): A session reference such as s-0123abcd, from refx_start or refx_status
- `venue` (string): Optional venue ID the referee named, without spaces

### `refx_status` (~186 tokens)

refereekit: status

Where one refereekit session stands, or a line for each session. Codes and counts only. PASS: the check's own guarantee holds, and nothing more. Quotation: the quoted words occur on the named page. Figure: a caption carries its label; what it shows is unchecked. FLAG: the page exists; its wording or an equation's label is unchecked. FAIL: the words are not on that page, the page does not exist or was not named, or a figure label was not found. It never shows the paper lacks them. A draft citing it is flagged. UNANCHORED: a quotation or equation with no clear page; unchecked. A clean finish: nothing is missing and nothing FAILs. It is not approval.

Input parameters:

- `session` (string): A session reference such as s-0123abcd, from refx_start or refx_status

### `refx_check` (~207 tokens)

refereekit: check

Check one of the session's drafts against the paper, without a model. Returns verdict counts and reason codes; the referee reads the details in the window. PASS: the check's own guarantee holds, and nothing more. Quotation: the quoted words occur on the named page. Figure: a caption carries its label; what it shows is unchecked. FLAG: the page exists; its wording or an equation's label is unchecked. FAIL: the words are not on that page, the page does not exist or was not named, or a figure label was not found. It never shows the paper lacks them. A draft citing it is flagged. UNANCHORED: a quotation or equation with no clear page; unchecked. A clean finish: nothing is missing and nothing FAILs. It is not approval.

Input parameters:

- `artifact` (string, required): report or editor
- `session` (string, required): A session reference such as s-0123abcd, from refx_start or refx_status

### `refx_finish` (~184 tokens)

refereekit: finish

Run the last deterministic checks on a refereekit session. Nothing is submitted or approved. PASS: the check's own guarantee holds, and nothing more. Quotation: the quoted words occur on the named page. Figure: a caption carries its label; what it shows is unchecked. FLAG: the page exists; its wording or an equation's label is unchecked. FAIL: the words are not on that page, the page does not exist or was not named, or a figure label was not found. It never shows the paper lacks them. A draft citing it is flagged. UNANCHORED: a quotation or equation with no clear page; unchecked. A clean finish: nothing is missing and nothing FAILs. It is not approval.

Input parameters:

- `session` (string, required): A session reference such as s-0123abcd, from refx_start or refx_status

### `refx_draft` (~86 tokens)

refereekit: draft

Open the review window at the report or the editor letter. The referee types the section lengths or the answers for the editor there and reads the draft there; refx_status shows when it is written.

Input parameters:

- `artifact` (string, required): report or editor
- `session` (string): A session reference such as s-0123abcd, from refx_start or refx_status

### `refx_open` (~175 tokens)

refereekit: open a view

Open one of the referee's private views in a window on the referee's own screen: review (the questions, the verdict and both drafts), drafts (read, check and edit a draft in the referee's editor), flags (what needs attention), note (venue notes), finish (the finishing checks), tutorial (a practice review) or setup (the reviews folder's page: model access, where the referee enters the backend, its key and the attestation, and the OpenReview account; it needs no session). The referee types and reads everything there; the result says whether the window opened.

Input parameters:

- `session` (string): A session reference such as s-0123abcd, from refx_start or refx_status
- `view` (string, required): review, drafts, flags, note, finish, tutorial or setup

### `refx_close` (~160 tokens)

refereekit: delete a session

Delete one refereekit session. The referee is asked on their own screen, with what the deletion destroys; the session goes only on their yes there, never on a tool argument. If the session holds venue notes, pass notes_to (a database path the referee named) or drop_notes as the referee decided. The result is the dry run's counts, the deletion's, or the window that asks.

Input parameters:

- `drop_notes` (boolean): true when the referee chose to discard the session's venue notes
- `notes_to` (string): A database path the referee named, to keep the session's venue notes in
- `session` (string, required): A session reference such as s-0123abcd, from refx_start or refx_status

### `refx_setup` (~154 tokens)

refereekit: remove or reinstall the agent integration

Remove refereekit's agent integration from this reviews folder (uninit), or reinstall it here (reinit). The referee is asked on their own screen, with what it would change; it happens only on their yes there, never on a tool argument. Sessions and the referee's own files are never touched. The result is the dry run's counts, the change's, or the window that asks.

Input parameters:

- `action` (string, required): uninit or reinit
- `profile` (string): Optional for reinit: core or full
- `tools` (string): Optional: the agents, comma-separated, among claude, codex and pi; uninit removes all by default, reinit reinstalls those installed

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-inferweave-refereekit/refereekit#diagnostics

## Score history

- 2026-11-05: 66
- 2026-11-04: 66
- 2026-11-03: 51
- 2026-11-02: 51
- 2026-11-01: 51
- 2026-10-31: 51

## Common questions

### What is the refereekit MCP server?

refereekit is an MCP server listed in the public MCP registry as com.inferweave/refereekit. Confidential peer review that checks a paper's citations. Set up from the install page first. This page covers its PyPI package (refereekit).

### Is the refereekit MCP server safe to use?

refereekit scores 66 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the refereekit MCP server expose?

refereekit exposes 8 tools: refx_start, refx_status, refx_check, refx_finish, refx_draft, and 3 more. Their descriptions and schemas cost roughly 1,251 tokens of context every time the server is loaded.

### Is the refereekit MCP server still maintained?

refereekit is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the refereekit MCP server under?

refereekit declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the refereekit MCP server?

VerifyMCP ran 15 checks on refereekit, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about refereekit: Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/refereekit/
- Socket report: https://socket.dev/pypi/package/refereekit
- Repository: https://github.com/junipertcy/refereekit
- Website: https://inferweave.com/refereekit/docs/install/
- Changelog RSS feed: https://verifymcp.io/servers/com-inferweave-refereekit/refereekit.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-inferweave-refereekit/refereekit/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-inferweave-refereekit/refereekit.json
- HTML version of this page: https://verifymcp.io/servers/com-inferweave-refereekit/refereekit