refereekit
PYPI · REFEREEKIT
Confidential peer review that checks a paper's citations. Set up from the install page first.
Available components
Last scanned (5 hours ago)
Scores higher than 63% of PyPI servers
Category Education and Research
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. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 2 of 14 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 5 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability61
- AI-judged instruction clarity (good).Pass
- 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. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 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. See how to fix → Fail
- An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
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.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 31 Oct 26 51
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed pypi/refereekit@1.0.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 14 packages
| Packages resolved | 14 |
|---|---|
| No linked repository | 2 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
refx_check refereekit: check ~207
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.
| Name | Type | Req | Description |
|---|---|---|---|
| artifact | string | yes | report or editor |
| session | string | yes | A session reference such as s-0123abcd, from refx_start or refx_status |
No output schema declared.
No examples provided.
refx_close refereekit: delete a session ~160
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.
| Name | Type | Req | Description |
|---|---|---|---|
| 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 | yes | A session reference such as s-0123abcd, from refx_start or refx_status |
No output schema declared.
No examples provided.
refx_draft refereekit: draft ~86
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.
| Name | Type | Req | Description |
|---|---|---|---|
| artifact | string | yes | report or editor |
| session | string | – | A session reference such as s-0123abcd, from refx_start or refx_status |
No output schema declared.
No examples provided.
refx_finish refereekit: finish ~184
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.
| Name | Type | Req | Description |
|---|---|---|---|
| session | string | yes | A session reference such as s-0123abcd, from refx_start or refx_status |
No output schema declared.
No examples provided.
refx_open refereekit: open a view ~175
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.
| Name | Type | Req | Description |
|---|---|---|---|
| session | string | – | A session reference such as s-0123abcd, from refx_start or refx_status |
| view | string | yes | review, drafts, flags, note, finish, tutorial or setup |
No output schema declared.
No examples provided.
refx_setup refereekit: remove or reinstall the agent integration ~154
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.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | 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 |
No output schema declared.
No examples provided.
refx_start refereekit: start ~99
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.
| Name | Type | Req | Description |
|---|---|---|---|
| string | yes | 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 |
No output schema declared.
No examples provided.
refx_status refereekit: status ~186
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.
| Name | Type | Req | Description |
|---|---|---|---|
| session | string | – | A session reference such as s-0123abcd, from refx_start or refx_status |
No output schema declared.
No examples provided.
How do I install the refereekit MCP server?
refereekit runs locally as a PyPI package, launched with uvx refereekit. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · refereekit
claude mcp add com-inferweave-refereekit -- uvx refereekit
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.