Corollary — scientific AI models, tools and databases MCP server
com.corollary-labs/corollarycorollary-labs.comstreamable-httpv1.0.0Scanned
Find open biology and chemistry AI models, bioinformatics tools and databases, and run them online.
6 tools: 1 change things and 5 only read.
- Reads private data · 1
- Reads text others write · 2
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes things. 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 Corollary — scientific AI models, tools and databases MCP server can do
The Corollary — scientific AI models, tools and databases MCP server is published by corollary-labs.com, a domain the MCP Registry verified. It has 6 tools. It can create or change data (1 tool: how_to_run_science_task), but cannot delete data. 5 tools only read.
1 tool reads private data (search_scientific_ai); 2 tools bring in text other people can write (list_science_tasks and list_scientific_ai_tasks).
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.
Last scanned Nov 12, 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.
6 tools
Changes things 1Claude Code: ask
how_to_run_science_taskFor a piece of scientific work someone wants done — 'annotate a phage genome', 'deconvolve bulk RNA-seq into cell types', 'check assembly completeness', 'dock a ligand', 'fit an IC…1 finding
Why it is in this group
- The name "how_to_run_science_task" says "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "how_to_run_science_task" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "how_to_run_science_task" says "run": a word for a change.
Description, as the server wrote it For a piece of scientific work someone wants done — 'annotate a phage genome', 'deconvolve bulk RNA-seq into cell types', 'check assembly completeness', 'dock a ligand', 'fit an IC50', 'process accelerometer data', 'call variants', 'find CRISPR arrays' — return how it is done on Corollary: the stages in order, the programs, models and databases used, what commonly goes wrong, and the page that starts it. Use this when the user wants a task done rather than a model named.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
Only reads 5Show 5 read-only tools
compare_scientific_ai_for_taskFor a task such as 'protein structure prediction', 'protein design', 'antibody design', 'molecular docking', 'single-cell', 'ADMET', 'phage genomics' or 'CRISPR', return every mode…No findings
Why it is in this group
- The name "compare_scientific_ai_for_task" says "compare": a word for reading.
Description, as the server wrote it For a task such as 'protein structure prediction', 'protein design', 'antibody design', 'molecular docking', 'single-cell', 'ADMET', 'phage genomics' or 'CRISPR', return every model or tool Corollary lists for it — what each does, licence, whether it runs online — and guidance on how to choose between them.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_scientific_ai_detailsFull reference for one entry: what it is, how it works, key facts, uses, strengths, limitations, citation, licence, and how to run it on Corollary.No findings
Why it is in this group
- The name "get_scientific_ai_details" says "get": a word for reading.
Description, as the server wrote it Full reference for one entry: what it is, how it works, key facts, uses, strengths, limitations, citation, licence, and how to run it on Corollary. Pass a name ('RFdiffusion'), an id ('esmfold2', 'nf-core/rnaseq', 'facebook/esm2_t33_650M_UR50D') or a corollary-labs.com URL.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
list_science_tasksEvery scientific analysis Corollary has a page and a method for, with its URL.Reads text others writeNo findings
Why it is in this group
- The name "list_science_tasks" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
Description, as the server wrote it Every scientific analysis Corollary has a page and a method for, with its URL.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
list_scientific_ai_tasksThe task categories Corollary compares models and tools in, with a page URL for each.Reads text others writeNo findings
Why it is in this group
- The name "list_scientific_ai_tasks" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
Description, as the server wrote it The task categories Corollary compares models and tools in, with a page URL for each.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
search_scientific_aiSearch Corollary's catalogue of open scientific AI models (protein structure prediction, protein design, docking, antibodies, genomics, single-cell, chemistry/ADMET, simulation, pa…Reads private dataNo findings
Why it is in this group
- The name "search_scientific_ai" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "search" and "database": it reads databases.
Description, as the server wrote it Search Corollary's catalogue of open scientific AI models (protein structure prediction, protein design, docking, antibodies, genomics, single-cell, chemistry/ADMET, simulation, pathology, weather), bioinformatics programs (BUSCO, samtools, BLAST…), scientific databases (UniProt, PDB, gnomAD…), nf-core pipelines and datasets. Each result says what it does, its licence and whether it can be run online on Corollary with no GPU or installation, with the page URL. Use it when a user asks which model or tool to use for a biology or chemistry task, or where to run one.
Annotations the server declares
- readOnlyHint: 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 outbound.
- Reads private data1
- 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 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, 18:36 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
- 1
- 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 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://corollary-labs.com/mcp: tools/list returned 6 tools to an anonymous client, including how_to_run_science_task (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "how_to_run_science_task" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "how_to_run_science_task" says "run": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http corollary https://corollary-labs.com/mcpclaude mcp add --transport http corollary https://corollary-labs.com/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__corollary__search_scientific_ai",
"mcp__corollary__get_scientific_ai_details",
"mcp__corollary__compare_scientific_ai_for_task",
"mcp__corollary__list_science_tasks",
"mcp__corollary__list_scientific_ai_tasks"
],
"ask": [
"mcp__corollary__how_to_run_science_task"
],
"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 corollary. Review it before you use it.
Capability tags behind 3 rules
- mcp__corollary__search_scientific_ai private-data
- mcp__corollary__list_science_tasks untrusted-input
- mcp__corollary__list_scientific_ai_tasks 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/com.corollary-labs/corollary/verify?hash=785aa09e704476c44582270028c25e79b3c4c455498de31f687dee273236e161" | jq -e '.changed == false'Pinned hash 785aa09e7044, from Nov 12, 2026, 23:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.corollary-labs/corollary/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.corollary-labs/corollary)Source: MCP Registry. Synced Oct 21, 2026, 17:53 UTC.
Corollary — scientific AI models, tools and databases MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Corollary — scientific AI models, tools and databases MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, 1 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 Corollary — scientific AI models, tools and databases MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Corollary — scientific AI models, tools and databases 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 Corollary — scientific AI models, tools and databases MCP server have?
- 6 tools: 1 write, 5 read. how_to_run_science_task, search_scientific_ai, get_scientific_ai_details, compare_scientific_ai_for_task, list_science_tasks and list_scientific_ai_tasks.
Does the Corollary — scientific AI models, tools and databases MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Corollary — scientific AI models, tools and databases MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Corollary — scientific AI models, tools and databases MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 12, 2026.