🔗 GitHub: github.com/CrackingShells
🐣 Early-stage, hackathon-driven, and growing.
🔗 github.com/Augmented-Na...
#AIForScience #Biology
🔗 github.com/Augmented-Na...
#AIForScience #Biology
🔗 www.anthropic.com/engineering/...
Exactly the kind of resource to share with your coding agent before tackling a server. I appreciate the didactic effort. 🐣
#AIForScience
🔗 www.anthropic.com/engineering/...
Exactly the kind of resource to share with your coding agent before tackling a server. I appreciate the didactic effort. 🐣
#AIForScience
After a closed first edition in August, we’re back open to all! Join up to 50 researchers/engineers to build MCP servers for scientific applications.
🔗 Sign up: forms.gle/vhTcV4uGDK9f...
Details⬇️
#AIForScience #OpenScience
After a closed first edition in August, we’re back open to all! Join up to 50 researchers/engineers to build MCP servers for scientific applications.
🔗 Sign up: forms.gle/vhTcV4uGDK9f...
Details⬇️
#AIForScience #OpenScience
MCP was barely known there. All the more reason for Cracking Shells to exist: simplifying onboarding for researchers.
#AIForScience
MCP was barely known there. All the more reason for Cracking Shells to exist: simplifying onboarding for researchers.
#AIForScience
🔗 paper-search: hub.docker.com/r/mcp/paper-search
🔗 arxiv-mcp-server: hub.docker.com/r/mcp/arxiv-mcp-server
Useful for automating literature discovery in #AIForScience workflows. Have you tried them yet?
#MCP #OpenScience
🔗 paper-search: hub.docker.com/r/mcp/paper-search
🔗 arxiv-mcp-server: hub.docker.com/r/mcp/arxiv-mcp-server
Useful for automating literature discovery in #AIForScience workflows. Have you tried them yet?
#MCP #OpenScience
Shoutout to @genomoncology.bsky.social !
Search PubMed, ClinicalTrials, cBioPortal...Fetch genes/variants, expand disease synonyms, match trials to biomarkers, analyze OpenFDA safety data...
🔗 biomcp.org
(Had forgotten about that one🤦)
#AIForScience
Shoutout to @genomoncology.bsky.social !
Search PubMed, ClinicalTrials, cBioPortal...Fetch genes/variants, expand disease synonyms, match trials to biomarkers, analyze OpenFDA safety data...
🔗 biomcp.org
(Had forgotten about that one🤦)
#AIForScience
Hatch! 0.7.0 now lets you add MCP packages with one command—It's multi-dependencies and multi-host.
Finally some versatility for #MCP setup 🐣
Still a pre-release, bug fixes & docs in progress!
#AIForScience
Hatch! 0.7.0 now lets you add MCP packages with one command—It's multi-dependencies and multi-host.
Finally some versatility for #MCP setup 🐣
Still a pre-release, bug fixes & docs in progress!
#AIForScience
trip.riken.jp/en/aijam/ind...
A hands-on event where scientists collaborate with LLMs from AWS, Anthropic, Google, and OpenAI to tackle challenging #research problems.
📆Dec 16-18: Main Session (Tokyo/Kobe) with on-site support from AI experts.
#AIForScience
trip.riken.jp/en/aijam/ind...
A hands-on event where scientists collaborate with LLMs from AWS, Anthropic, Google, and OpenAI to tackle challenging #research problems.
📆Dec 16-18: Main Session (Tokyo/Kobe) with on-site support from AI experts.
#AIForScience
A couple more of well-documented ones to explore:
🔗 Graph-based (for knowledge graphs): ArangoDB github.com/PCfVW/mcp-ar...
🔗 Document-based (for descriptive data): MongoDB github.com/mcp/mongodb-...
#MCP #AI #Dev #TechStack
A couple more of well-documented ones to explore:
🔗 Graph-based (for knowledge graphs): ArangoDB github.com/PCfVW/mcp-ar...
🔗 Document-based (for descriptive data): MongoDB github.com/mcp/mongodb-...
Find what you need faster at: github.blog/ai-and-ml/gi...
#GitHub #MCP #Developer #AI #OpenSource
Find what you need faster at: github.blog/ai-and-ml/gi...
#GitHub #MCP #Developer #AI #OpenSource
We’re tackling this too at Cracking Shells (ETA: December). The more minds on it, the faster we’ll crack it. 🐣
#MCP #AIForScience
t.co/imtblSlxE5
#AI #MCP #Tech #AITools
We’re tackling this too at Cracking Shells (ETA: December). The more minds on it, the faster we’ll crack it. 🐣
#MCP #AIForScience
But the top one for us remains the encapsulation and being able to (almost) drop it anywhere. This is so convenient to decouple dev work from actual agent systems, particularly in #science
#AIAgents #MCP #AITools #Developer
#AIForScience
www.biorxiv.org/content/10.1...
#AIForScience
www.biorxiv.org/content/10.1...
1. Not a perfect fit for #MCP for #science (yet), but that’s okay because 👇
2. Recommend filtering of existing registries AND
3. Support for custom package registries: the whole point of Cracking Shells 🤩—MCP servers for scientific applications
At Cracking Shells, we’ve built our own solutions, but we’re all for interoperability. Excited to test, compare, and adapt to what serves the community best.
#AIForScience
Explore the repo:
github.com/modelcontext...
#MCP #AI #OpenSource #Developer
At Cracking Shells, we’ve built our own solutions, but we’re all for interoperability. Excited to test, compare, and adapt to what serves the community best.
#AIForScience
That could transfer to #LabAutomation e.g., routing logs from robotic systems or equipment notifications to research trackers.
That could work today with systems we already have.
#MCP #AIForScience
That could transfer to #LabAutomation e.g., routing logs from robotic systems or equipment notifications to research trackers.
That could work today with systems we already have.
#MCP #AIForScience
London, Oct 2. Register at mcpdevsummit.ai
#OpenSource #Decentralization #AI #TechTalks
London, Oct 2. Register at mcpdevsummit.ai
#OpenSource #Decentralization #AI #TechTalks
#TechTalks #AIagents #LondonTech #MCP
#TechTalks #AIagents #LondonTech #MCP
None had used MCP or LLMs APIs before. By the end, they’d created their own MCP servers.
This was invite-only, but more events are coming! 🐣 #AIForScience
None had used MCP or LLMs APIs before. By the end, they’d created their own MCP servers.
This was invite-only, but more events are coming! 🐣 #AIForScience
🗓️ Oct 2|London
mcpdevsummit.ai
#MCPDevSummit #AISecurity #MCP #Ai
🗓️ Oct 2|London
mcpdevsummit.ai
#MCPDevSummit #AISecurity #MCP #Ai
Small: the decorator pattern of the Python SDK is a killer to wrap existing API
Decoupled: Devs build tools; users install them like packages (almost). Fits the ‘publish once, use anywhere’ model scientists like.
We'll be sharing more about it. In the meantime, take a look: github.com/CrackingShells
We'll be sharing more about it. In the meantime, take a look: github.com/CrackingShells