Corollary — scientific AI models, tools and databases
Find open biology and chemistry AI models, bioinformatics tools and databases, and run them online.
我该使用它吗
质量与安全性
发现（2）
- LOWTool 'list_science_tasks' description lacks action verb在 list_science_tasks 中
- LOWTool 'list_scientific_ai_tasks' description lacks action verb在 list_scientific_ai_tasks 中
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"corollary": {
"url": "https://corollary-labs.com/mcp"
}
}
}远程端点
https://corollary-labs.com/mcpstreamable-http它能做什么
工具清单
工具（6）
🟢search_scientific_ai(query, kind, limit)
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.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Name or task, e.g. 'ESMFold', 'protein-ligand binding affinity', 'phage annotation'."
},
"kind": {
"type": "string",
"enum": [
"any",
"model",
"dataset",
"software",
"database",
"pipeline"
],
"description": "Restrict to one kind. Default: any."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 25,
"description": "Default 10."
}
},
"required": [
"query"
],
"additionalProperties": false
}🟢get_scientific_ai_details(ref)
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.
输入模式
{
"type": "object",
"properties": {
"ref": {
"type": "string",
"description": "Name, id or Corollary page URL."
}
},
"required": [
"ref"
],
"additionalProperties": false
}🟢compare_scientific_ai_for_task(task)
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.
输入模式
{
"type": "object",
"properties": {
"task": {
"type": "string",
"description": "The task, in plain words."
}
},
"required": [
"task"
],
"additionalProperties": false
}🟢how_to_run_science_task(task)
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.
输入模式
{
"type": "object",
"properties": {
"task": {
"type": "string",
"description": "The work the user wants done, in plain words."
}
},
"required": [
"task"
],
"additionalProperties": false
}🟢list_science_tasks
Every scientific analysis Corollary has a page and a method for, with its URL.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢list_scientific_ai_tasks
The task categories Corollary compares models and tools in, with a page URL for each.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}社区
证据