Skip to content

Crivum MCP server

org.crivum/crivumcrivum.orgstreamable-httpv1.0.0Scanned

Score academic and professional writing against published criteria with three reference models.

4 tools: 2 change things and 2 only read.

Tools: 0 delete, 0 irreversible, 2 write, 2 read.
  • Reads private data · 0
  • Reads text others write · 0
  • Can send data out · 0
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 Crivum MCP server can do

The Crivum MCP server is published by crivum.org, a domain the MCP Registry verified. It has 4 tools. It can create or change data (2 tools: screen_text and evaluate_text), but cannot delete data. 2 tools only read.

None of its tools reads private data, brings in text other people write, or sends data out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 19, 2026, version 1.0.0.

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.

4 tools

Changes things 2Claude Code: ask
  • evaluate_textScore a text against published academic criteria.No findings

    Why it is in this group

    • The name "evaluate_text" says "evaluate": a word for a change.
    Description, as the server wrote it
    Score a text against published academic criteria. Use when a user wants to know how strong a paper, case report, thesis chapter or teaching material is, or wants a reviewable score before submitting it somewhere. Returns a 0 to 100 score, a per criterion breakdown, the divergence between three reference models and whether the work qualifies for a citable DOI record. Does not accept recipes, operational legal documents, workout plans or other how to instructions. This is not peer review and the score is not an accreditation. Crivum reads any language and answers in the language of the text, and the criteria were calibrated in Portuguese and English, so comparing results across languages is a reading nobody has measured yet. Requires an API key. Gatilho em português: "quero saber a nota do meu texto antes de submeter".
  • screen_textCheck whether a draft is ready before spending anything on it.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.
    Description, as the server wrote it
    Check whether a draft is ready before spending anything on it. Returns a 0 to 100 readiness reading, the suggested work type and up to six objective questions about what is still missing. Runs on a single cheap model and needs no API key, so it is the right first call when a user asks if a paper, case report, thesis chapter or teaching material is good enough yet. For the score that counts, with three reference models and eligibility for a citable record, call evaluate_text afterwards. Gatilho em português: "meu texto já está bom o suficiente".
Only reads 2Show 2 read-only tools
  • get_criteriaReturn Crivum's public rubric by work type, the tier ladder, the thresholds, the minimum score for a citable record and what Crivum accepts and refuses, each with a version number.No findings

    Why it is in this group

    • The name "get_criteria" says "get": a word for reading.
    Description, as the server wrote it
    Return Crivum's public rubric by work type, the tier ladder, the thresholds, the minimum score for a citable record and what Crivum accepts and refuses, each with a version number. No API key required. Use before calling evaluate_text, or to show a user what a score decomposes into. Gatilho em português: "quais são os critérios da Crivum".
  • verify_recordList Crivum's published, citable records (title, authors, DOI when registered, tier and score).No findings

    Why it is in this group

    • The description's first verb is "list": a word for reading.
    Description, as the server wrote it
    List Crivum's published, citable records (title, authors, DOI when registered, tier and score). Pass exactly one of slug, doi or codigo to check one specific record, or omit all three to browse recent registrations. Rejects calls that pass more than one identifier at once, instead of matching either. No API key required. Gatilho em português: "esse trabalho já tem registro na Crivum".

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 or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
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.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:17 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
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://crivum.org/mcp: tools/list returned 4 tools to an anonymous client, including screen_text (write), evaluate_text (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools1 changed.~1 changedView diff

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http crivum https://crivum.org/mcp
claude mcp add --transport http crivum https://crivum.org/mcp

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__crivum__get_criteria",
      "mcp__crivum__verify_record"
    ],
    "ask": [
      "mcp__crivum__screen_text",
      "mcp__crivum__evaluate_text"
    ],
    "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 crivum. Review it before you use it.

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/org.crivum/crivum/verify?hash=c06bdd37a95640a28b448e3e39a3703c651bb3f611118ea66a6b34ea95e8e519" | jq -e '.changed == false'

Pinned hash c06bdd37a956, from Nov 19, 2026, 00:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/org.crivum/crivum/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for org.crivum/crivum
[![Anlyon Radar](https://radar.anlyon.com/badge/org.crivum/crivum.svg)](https://radar.anlyon.com/servers/org.crivum/crivum)

Source: MCP Registry. Synced Oct 21, 2026, 18:54 UTC.

Crivum MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Crivum MCP server safe?

No scan can promise that. What its definitions show: 4 tools, 2 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Crivum MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Crivum MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Crivum MCP server have?

4 tools: 2 write, 2 read. screen_text, evaluate_text, get_criteria and verify_record.

Does the Crivum MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Crivum MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Crivum MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 5, 2026. Every change is on this page and in its Atom feed.