Life Sciences: Anthropic's marketplace for Claude Code
Life Sciences Marketplace
Anthropic's official plugin marketplace for biology and medicine: PubMed, BioRender, Synapse, ChEMBL, ClinicalTrials.gov and data analysis skills
- 632 ★ on the repository
- Last commit
Extended access
Why this level
- The plugins connect external servers and databases over the network, and some ask for tokens or accounts
- Pipeline skills run code and Docker on your machine (for example nextflow-development)
Install
- Works in
Manual install
/plugin marketplace add anthropics/life-sciencesThen install the plugins you need, for example /plugin install pubmed@life-sciences.
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The plugins connect external servers and databases over the network, and some ask for tokens or accounts
- Pipeline skills run code and Docker on your machine (for example nextflow-development)
This is third-party code. Review the repository files before installing.
What it does
The repository holds a marketplace.json for Claude Code, prepared for the Claude for Life Sciences launch. One command, /plugin marketplace add anthropics/life-sciences, connects the catalogue, and you then install plugins by name such as pubmed@life-sciences. marketplace.json lists 21 plugins. Some plugins connect external MCP servers: PubMed, BioRender, Synapse.org, Wiley Scholar Gateway, bioRxiv and medRxiv, ClinicalTrials.gov, ChEMBL, Open Targets, Consensus, Medidata, and the paid Cortellis and AdisInsight. 10x Genomics Cloud runs as a local MCPB server. The other plugins are skills: single-cell RNA-seq quality control following scverse practice, converting instrument data to the Allotrope format, running nf-core pipelines through Nextflow (rnaseq, sarek, atacseq), working with scvi-tools, drafting clinical trial protocols and choosing a scientific problem with the Fischbach and Walsh method. The MCP servers themselves are not stored in this repository; they stay with their providers.
Who it is for. For researchers, bioinformaticians and analysts in biology and medicine who work in Claude Code and want to attach databases and methods with one command.
Good fit when
- You need biomedical literature search from Claude Code: the pubmed plugin works without an account
- You need quality control for single-cell RNA-seq with MAD filtering and plots
- You want to run public GEO or SRA data through nf-core pipelines: rnaseq, sarek or atacseq
- You need to draft a clinical trial protocol from an FDA or NIH template
- You are shaping a project idea and want a structured way to choose a scientific problem and review weak points
Not a fit when
- You need the MCP servers themselves as code: the repository does not store them, only connection descriptions
- You have no subscriptions to commercial services: Cortellis and AdisInsight need paid access and 10x Genomics is useful only with data in your account
- You want to run Nextflow without Docker and Nextflow installed locally: the skill needs both
- You work outside Claude Code: the /plugin commands belong to it
- You need medical advice or a clinical decision: these are tools for researchers
Example request
Search PubMed for recent work on CAR-T therapy and pick out papers that include clinical trial dataLimitations
The connected services live with their providers and have their own terms: only PubMed works without an account, BioRender, Synapse, Wiley Scholar Gateway and Consensus need a free account, and Cortellis, AdisInsight and 10x Genomics need a paid or institutional subscription. The nextflow-development skill needs Docker and Nextflow. Server licences are set by their providers. Last commit on August 14, 2026. Anthropic takes bug reports about the Claude Code plugin system in its own support channel, while questions about individual servers go to their providers. The Benchling plugin was removed because its server addresses depend on the tenant.
How to disable. Remove a plugin with /plugin uninstall pubmed@life-sciences (using the plugin's name) or open /plugin, Manage plugins. The marketplace itself is removed in the same menu.
FAQ
How do I connect PubMed to Claude Code?
Run /plugin marketplace add anthropics/life-sciences, then /plugin install pubmed@life-sciences and restart Claude Code. No account is needed.
Which plugins does the marketplace have?
marketplace.json lists 21 plugins. MCP servers: pubmed, biorender, synapse, wiley-scholar-gateway, biorxiv, clinical-trials, chembl, owkin, open-targets, tooluniverse, medidata, consensus, cortellis, adisinsight and 10x-genomics. Skills: single-cell-rna-qc, instrument-data-to-allotrope, nextflow-development, scvi-tools, clinical-trial-protocol and scientific-problem-selection.
How do I set credentials for plugins that need sign-in?
Open /plugin, choose Manage plugins, find the installed server, choose Configure, enter the details and restart Claude Code. Some servers ask you to sign in through their own web interface.
How is it different from the science skill sets in the catalog?
This marketplace is official, from Anthropic, and mostly connects providers' external MCP servers. Sets such as science-skills and scientific-agent-skills consist of their own skills.
What does the nextflow-development skill need?
Docker and Nextflow installed on your machine. The skill runs the nf-core rnaseq, sarek and atacseq pipelines on local or public GEO and SRA data and suggests a suitable pipeline.
Discussion
No questions or reviews yet.
Related
PluginsA Claude Code plugin and MCP server: over 1000 scientific tools for biology, chemistry and medicine, data-check commands and routing skills
A plugin marketplace for Claude Code and GitHub Copilot on Power BI and Microsoft Fabric: semantic models, DAX, TMDL, reports
BioMCP
biomcp
One binary and a single command grammar for 70 biomedical sources: PubMed, ClinVar, ClinicalTrials.gov, OncoKB. MCP mode starts with the serve command
An MCP server for searching and downloading academic papers from arXiv, PubMed, bioRxiv, Semantic Scholar and other open sources
A Google DeepMind skill collection for science tasks: access to biology and chemistry databases, literature search and structural biology
MCP server that connects Claude Code and Codex to an open R or Python session in RStudio and Positron, where your data lives
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| Life Sciences: Anthropic's marketplace for Claude Code (this entry) | yes | 632 | ||
| Science Skills | no | 3,354 | Google DeepMind's own skill set for science | |
| Scientific Agent Skills | no | 55,112 | a large set of science skills with database access, not a marketplace | |
| BioMCP | no | not required | 668 | one binary with commands for biomedical sources and an MCP mode |
README in short
The README opens with a quick start of three commands, then lists plugins with their identifiers and account requirements: remote MCP servers, the local 10x Genomics server and five skills. It ends with credential setup through the /plugin menu, a summary of authentication requirements and a note on the Benchling plugin, removed because it uses tenant-specific URLs.