Cerebrum MCP server
org.askcerebrum/cerebrumaskcerebrum.orgstreamable-httpv1.0.0Scanned
Search the scientific literature and get a cited answer, plus the Trending in Science edition.
4 tools: 4 only read.
- Reads private data · 0
- Reads text others write · 4
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- 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 Cerebrum MCP server can do
The Cerebrum MCP server is published by askcerebrum.org, a domain the MCP Registry verified. It has 4 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
4 tools bring in text other people can write (search_literature, get_trending, get_statements and 1 more).
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 2 times since Anlyon Radar first saw them.
Last scanned Nov 18, 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
Only reads 4Show 4 read-only tools
get_reception_reportBuild the standing reception report for one paper: the citation statement counts Cerebrum holds for it, the reception tallies served via scite.ai, and its retraction status under t…Reads text others writeNo findings
Why it is in this group
- The name "get_reception_report" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Build the standing reception report for one paper: the citation statement counts Cerebrum holds for it, the reception tallies served via scite.ai, and its retraction status under the multi signal rule, where a paper counts as retracted only when at least two of the three checking channels agree. A clean read prints no retraction line at all, and a status no channel could settle is reported as unknown.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
get_statementsLook up what later papers say about a paper, in the citing sentences Cerebrum has collected and classified for it.Reads text others writeNo findings
Why it is in this group
- The name "get_statements" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Look up what later papers say about a paper, in the citing sentences Cerebrum has collected and classified for it. Returns, for each DOI, whether its sentences are ready, still being collected, or settled empty, the counts by stance, and the sentences themselves, each with two separate labels: the stance Cerebrum assigned and the purpose Semantic Scholar recorded. A paper still being collected is reported as collecting, never as holding nothing.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
get_trendingGet the current Today in Science edition and return the top headlines grouped by section with links to the original stories.Reads text others writeNo findings
Why it is in this group
- The name "get_trending" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get the current Today in Science edition and return the top headlines grouped by section with links to the original stories.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
search_literatureSearch the scientific literature for a research question and return a cited answer with a numbered source list.Reads text others writeNo findings
Why it is in this group
- The name "search_literature" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Search the scientific literature for a research question and return a cited answer with a numbered source list. Use this when you need evidence from papers rather than general knowledge.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
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 outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write4
- 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.
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
- 0
- Protocol version
- 2025-03-26
- 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
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.
Tools2 added.+2 addedView diff
- Added:get_reception_reportOnly reads
- Added:get_statementsOnly reads
Tools1 changed.~1 changedView diff
- Changed:get_trendingOnly readstitledescription
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http cerebrum https://askcerebrum.org/mcpclaude mcp add --transport http cerebrum https://askcerebrum.org/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__cerebrum__search_literature",
"mcp__cerebrum__get_trending",
"mcp__cerebrum__get_statements",
"mcp__cerebrum__get_reception_report"
],
"ask": [],
"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 cerebrum. Review it before you use it.
Capability tags behind 4 rules
- mcp__cerebrum__search_literature untrusted-input
- mcp__cerebrum__get_trending untrusted-input
- mcp__cerebrum__get_statements untrusted-input
- mcp__cerebrum__get_reception_report untrusted-input
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.askcerebrum/cerebrum/verify?hash=1f3b2461de59118782bc9b72fbc110135325108afeef06c2f04541c2fc22d46e" | jq -e '.changed == false'Pinned hash 1f3b2461de59, from Nov 18, 2026, 02:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/org.askcerebrum/cerebrum/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/org.askcerebrum/cerebrum)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:54 UTC.
Cerebrum MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Cerebrum MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the Cerebrum MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Cerebrum 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 Cerebrum MCP server have?
- 4 tools: 4 read. search_literature, get_trending, get_statements and get_reception_report.
Does the Cerebrum MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Cerebrum MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Cerebrum MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 18, 2026. Every change is on this page and in its Atom feed.