Malte Kuehl
@maltekuehl.com
250 followers 660 following 58 posts
Computational medicine @ AU Founder @ KH Biotechnology Creator of spatiomic, pytximport and BioContextAI Interested in spatial omics, immunology, cancer & ageing Lab: https://github.com/complextissue/ Personal: https://maltekuehl.com Opinions my own.
Posts Media Videos Starter Packs
maltekuehl.com
A truly helpful resource for all things omics! Make sure to check out their MCP server, too: biocontext.ai/registry/sae...
Reposted by Malte Kuehl
maltekuehl.com
It was a great pleasure to collaborate with this team - a quite different perspective on spatial omics, applying lessons from other scientific fields to biomedicine with robust spatial statistics. Thanks to everybody involved!

Tutorial available at: robinsonlabuzh.github.io/pasta/00-hom...
maltekuehl.com
If you are working with imaging-based proteomics, make sure to check out spatiomic.org, too, which includes many utility functions to apply lattice-based spatial statistics to your data.
maltekuehl.com
It was a great pleasure to collaborate with this team - a quite different perspective on spatial omics, applying lessons from other scientific fields to biomedicine with robust spatial statistics. Thanks to everybody involved!

Tutorial available at: robinsonlabuzh.github.io/pasta/00-hom...
Reposted by Malte Kuehl
sib.swiss
💫 The 2025 SIB Innovative Resource Award goes to @scverse.bsky.social 💫
The jury is impressed by the focus of these omics tools on interoperability, usability, and communication. The project’s solid governance and emphasis on open science principles are particularly commendable
#SIBawards #bc2basel
Ilan Gold accepting the award for scverse
maltekuehl.com
Interesting work by @slobentanzer.bsky.social and team, making BioCypher available through MCP! Check it out on biocontext.ai/registry/bio... or try it in BioContextAI Chat (biocontext.ai/chat, click "cogs" icon to add the remote MCP server).
biocontext.ai
🤖🧬 New biomedical MCP server added to the registry:
BioCypher Knowledge Graph MCP
Check it out at https://biocontext.ai/registry/biocypher/biocypher-mcp
maltekuehl.com
If you are interested in grounding language models in reality and enabling responsible agentic research applications that leverage existing knowledge and human-in-the-loop validation, check out biomedical MCP servers on biocontext.ai or follow @biocontext.ai to be notified about new servers.
BioContextAI
Biomedical context via the Model Context Protocol for agentic systems
biocontext.ai
maltekuehl.com
Interesting thoughts on using specialized small models for agentic systems. Potential to cut cost and build more sustainable and privacy-preserving local-first solutions?
arxiv.org/html/2506.02...
Small Language Models are the Future of Agentic AI
arxiv.org
maltekuehl.com
Great work by @jonsch.one and comleagues from @saezlab.bsky.social!
Reposted by Malte Kuehl
biocontext.ai
🤖🧬 New biomedical MCP server added to the registry:
Holy-BIO-MCP's gget server
Check it out at https://biocontext.ai/registry/longevity-genie/gget-mcp
Reposted by Malte Kuehl
saezlab.bsky.social
Glad to contribute to this collaborative community platform.
A case study shows MCP servers working together - combining BioContextAI Knowledgebase with our omnipath omnipathdb.org MCP (work in progress) to showcase interoperability. Looking forward to see how the ecosystem evolves!
maltekuehl.com
Preprint alert 🚨 Do you use chatbots in your work or even build MCP servers and agentic systems yourself?

Or would you like to find a way to use biomedical tools using natural language?

Then check out biocontext.ai, now out on bioRxiv: www.biorxiv.org/content/10.1...
Diagram showing MCP-enabled research architecture. Part A illustrates the flow between MCP servers (including BioContextAI Knowledgebase MCP and Community-developed MCP servers), Agentic systems connected via Model Context Protocol, and researchers asking research questions. MCP servers connect to knowledgebases and specialized software. Part B details the BioContextAI project components, divided into Registry (Schema.org ontology, Web interface, Open source licensing, MCP-enabled chatbot, Continuous integration) and Community (Documentation, Community forums, MCP server reviews, Shareable collections, Interoperability with tools like BioChatter).
Reposted by Malte Kuehl
maltekuehl.com
Preprint alert 🚨 Do you use chatbots in your work or even build MCP servers and agentic systems yourself?

Or would you like to find a way to use biomedical tools using natural language?

Then check out biocontext.ai, now out on bioRxiv: www.biorxiv.org/content/10.1...
Diagram showing MCP-enabled research architecture. Part A illustrates the flow between MCP servers (including BioContextAI Knowledgebase MCP and Community-developed MCP servers), Agentic systems connected via Model Context Protocol, and researchers asking research questions. MCP servers connect to knowledgebases and specialized software. Part B details the BioContextAI project components, divided into Registry (Schema.org ontology, Web interface, Open source licensing, MCP-enabled chatbot, Continuous integration) and Community (Documentation, Community forums, MCP server reviews, Shareable collections, Interoperability with tools like BioChatter).
maltekuehl.com
Working on this project has been a great privilege, thanks to the many contributions from all team members, including members from the @scverse.bsky.social and BioCypher communities.
maltekuehl.com
To stay up-to-date with new biomedical MCP servers, make sure to follow @biocontext.ai on Bluesky, where new additions to the Registry are automatically announced.

#biomedicalAI #MCP #agenticAI #agents
maltekuehl.com
If you are interested in building out the biomedical MCP ecosystem, we invite you to share your work through BioContextAI and to connect via GitHub (github.com/biocontext-ai) or through the @scverse.bsky.social Zulip (scverse.zulipchat.com), were you can find us in the "[wg] biocontext-ai" channel.
maltekuehl.com
In a fast-moving field of emerging standards, we view the Model Context Protocol as an opportunity to build FAIR4RS software that is open, interoperable and indexed. While dozens of tools have already been adapted as MCP servers, many more remain currently out of reach of agentic systems.
maltekuehl.com
You can also easily add it to existing chatbots like Claude Desktop, VS Code and others. Find out how in our README: github.com/biocontext-a...
Example Claude Desktop conversation, asking for summarized information from InterPro for human CREB1 with the chatbot using BioContextAI Knowledgebase MCP tools to answer the query.
maltekuehl.com
If you would like to explore how MCP servers might be helpful for your work, we provide a reference server called "Knowledgebase MCP" that integrates UniProt, STRING, PRIDE, InterPro, ClinicalTrials, EuropePMC and many more sources. You can start chatting at: biocontext.ai/chat
Example chat interaction, asking the chatbot for PRIDE studies looking into AIFM1, with a list provided after calling a tool from the MCP server.
maltekuehl.com
You can find the Registry here: biocontext.ai/registry

If you work on biomedical MCP servers, you can contribute it through GitHub or by clicking "Add Your Server". The Registry builds on standard Schema.org ontology and all listed servers have OSI-approved licenses.
MCP Server Registry | BioContextAI
Discover and integrate Model Context Protocol servers for biomedical applications
biocontext.ai
maltekuehl.com
With BioContextAI, we aim to index biomedical MCP servers (think: plugins for chatbots/agents) that expose specialized tools and knowledgebases to help foster a community of reusable components for AI 🤖 No matter, whether you would like to use existing chatbots or build your own biology agent 🧬
maltekuehl.com
Preprint alert 🚨 Do you use chatbots in your work or even build MCP servers and agentic systems yourself?

Or would you like to find a way to use biomedical tools using natural language?

Then check out biocontext.ai, now out on bioRxiv: www.biorxiv.org/content/10.1...
Diagram showing MCP-enabled research architecture. Part A illustrates the flow between MCP servers (including BioContextAI Knowledgebase MCP and Community-developed MCP servers), Agentic systems connected via Model Context Protocol, and researchers asking research questions. MCP servers connect to knowledgebases and specialized software. Part B details the BioContextAI project components, divided into Registry (Schema.org ontology, Web interface, Open source licensing, MCP-enabled chatbot, Continuous integration) and Community (Documentation, Community forums, MCP server reviews, Shareable collections, Interoperability with tools like BioChatter).
Reposted by Malte Kuehl