reviewpaper.ai MCP server
ai.reviewpaper/reviewpaperreviewpaper.aistreamable-httpv1.0.1Scanned
Review forms for 29 ML/NLP/CV venues, AI conference deadlines and ICLR acceptance odds.
7 tools: 1 do something that can't be undone, 1 change things and 5 only read.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 1
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the reviewpaper.ai MCP server can do
The reviewpaper.ai MCP server is published by reviewpaper.ai, a domain the MCP Registry verified. It has 7 tools. It can do things that cannot be undone, such as sending, paying or publishing (convert_score) and create or change data (1 tool: iclr_acceptance_odds), but cannot delete data. 5 tools only read.
2 tools bring in text other people can write (get_review_form and get_deadline); 1 tool can send data out of your system (convert_score).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 12, 2026, version 1.0.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
7 tools
Can't be undone 1Claude Code: ask
convert_scoreMap an overall review score at one venue to the same position on other venues' scales, keeping its distance from each venue's rough acceptance bar.Can send data out1 finding
Why it is in this group
- The name "convert_score" says "convert": a word for a change.
- The input addresses people (input.to): what it sends cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe input takes a destination (input.to): what the tool writes goes there.
Findings
- Warn
The server marks "convert_score" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "convert_score" says "convert": a word for a change.
Description, as the server wrote it Map an overall review score at one venue to the same position on other venues' scales, keeping its distance from each venue's rough acceptance bar. A heuristic for intuition, not an official equivalence.
Annotations the server declares
- title: Convert score
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Changes things 1Claude Code: ask
iclr_acceptance_oddsHistorical ICLR acceptance rate for papers with similar reviewer ratings, from public OpenReview decisions (kernel estimate over past score profiles).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Historical ICLR acceptance rate for papers with similar reviewer ratings, from public OpenReview decisions (kernel estimate over past score profiles). Give 3–6 ratings on the 0–10 scale ICLR used through 2026 (even numbers 0, 2, 4, 6, 8, 10; 2024–2025 used 1, 3, 5, 6, 8, 10). ICLR 2027 ratings are on a new 1–4 scale (clear reject, leaning reject, leaning accept, clear accept) with no acceptance history yet, so do not pass 2027 ratings here. Not a prediction of any decision.
Annotations the server declares
- title: ICLR odds
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 5Show 5 read-only tools
get_deadlineFull timeline for one conference edition: abstract/registration, paper, author response and decision dates (AoE + ISO), plus links to its review form.Reads text others writeNo findings
Why it is in this group
- The name "get_deadline" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
Description, as the server wrote it Full timeline for one conference edition: abstract/registration, paper, author response and decision dates (AoE + ISO), plus links to its review form. Accepts 'cvpr-2027', 'CVPR 2027' or just 'CVPR' (next upcoming edition).
Annotations the server declares
- title: Get deadline
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_llm_policyWhat a venue allows authors and reviewers to do with LLMs, with the official policy link.No findings
Why it is in this group
- The name "get_llm_policy" says "get": a word for reading.
Description, as the server wrote it What a venue allows authors and reviewers to do with LLMs, with the official policy link. Use before advising someone on AI use for a submission or a review.
Annotations the server declares
- title: LLM policy
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_review_formThe exact reviewer form for a venue: every field in order with guidance, each score scale with its official labels, the author checklist, the area-chair meta-review, the rough acce…Reads text others writeNo findings
Why it is in this group
- The name "get_review_form" says "get": a word for reading.
What it can reach
- untrusted-inputThe name "get_review_form" says "get" and "review": it reads comments, which other people can write.
- untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
Description, as the server wrote it The exact reviewer form for a venue: every field in order with guidance, each score scale with its official labels, the author checklist, the area-chair meta-review, the rough acceptance bar and the venue's LLM policy. Accepts a slug, name or alias (e.g. 'iclr', 'NeurIPS', 'ACL Rolling Review', 'cvpr').
Annotations the server declares
- title: Get review form
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_deadlinesUpcoming paper and abstract deadlines for ~64 ML, CV, NLP, robotics, speech, data-mining and AI conferences, soonest first, in AoE and ISO-8601 UTC.No findings
Why it is in this group
- The name "list_deadlines" says "list": a word for reading.
Description, as the server wrote it Upcoming paper and abstract deadlines for ~64 ML, CV, NLP, robotics, speech, data-mining and AI conferences, soonest first, in AoE and ISO-8601 UTC. Projected (not yet announced) dates are excluded unless include_estimated is true.
Annotations the server declares
- title: List deadlines
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_venuesList the 29 ML / NLP / CV / data-mining venues whose reviewer forms reviewpaper.ai models, with the overall score scale, whether the form is official or modeled, and links.No findings
Why it is in this group
- The name "list_venues" says "list": a word for reading.
Description, as the server wrote it List the 29 ML / NLP / CV / data-mining venues whose reviewer forms reviewpaper.ai models, with the overall score scale, whether the form is official or modeled, and links. Use get_review_form for the full form.
Annotations the server declares
- title: List venues
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:27 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 2
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (1 irreversible, 1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://reviewpaper.ai/mcp: tools/list returned 7 tools to an anonymous client, including convert_score (irreversible), iclr_acceptance_odds (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnconvert_score
The server marks "convert_score" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "convert_score" says "convert": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools1 changed.~1 changedView diff
- Changed:iclr_acceptance_oddsChanges thingsdescriptioninputSchema
Install
Pinned to version 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http reviewpaper https://reviewpaper.ai/mcpclaude mcp add --transport http reviewpaper https://reviewpaper.ai/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__reviewpaper__list_venues",
"mcp__reviewpaper__get_review_form",
"mcp__reviewpaper__list_deadlines",
"mcp__reviewpaper__get_deadline",
"mcp__reviewpaper__get_llm_policy"
],
"ask": [
"mcp__reviewpaper__iclr_acceptance_odds",
"mcp__reviewpaper__convert_score"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as reviewpaper. Review it before you use it.
Capability tags behind 3 rules
- mcp__reviewpaper__get_review_form untrusted-input
- mcp__reviewpaper__get_deadline untrusted-input
- mcp__reviewpaper__convert_score outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/ai.reviewpaper/reviewpaper/verify?hash=530cfd16cb6fded45d0c4cff324509b8a5bbd067b6631b92c3aa2f9d77c2f099" | jq -e '.changed == false'Pinned hash 530cfd16cb6f, from Nov 12, 2026, 05:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.reviewpaper/reviewpaper/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.reviewpaper/reviewpaper)Source: MCP Registry. Synced Nov 12, 2026, 05:17 UTC.
reviewpaper.ai MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the reviewpaper.ai MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 2 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the reviewpaper.ai MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the reviewpaper.ai MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: convert_score.
What tools does the reviewpaper.ai MCP server have?
- 7 tools: 1 irreversible, 1 write, 5 read. convert_score, iclr_acceptance_odds, list_venues, get_review_form, list_deadlines, get_deadline and get_llm_policy.
Does the reviewpaper.ai MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the reviewpaper.ai MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): convert_score.
Has the reviewpaper.ai MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 11, 2026. Every change is on this page and in its Atom feed.