1. Conduid
  2. Developer Tools
  3. Lynxkite 2000
MCP server · Developer Tools

Lynxkite 2000

by · github.com/lynxkite/lynxkite-2000

GPU-accelerated drug discovery, graph analytics, agentic workflows with a friendly face

Unclaimed AGPL-3.0 graphdevtoolsdata-science
InstallView source
62Good

Scored 4 days ago · breakdown

About Lynxkite 2000

Lynxkite 2000 is an MCP server published by lynxkite in the Developer Tools category: gPU-accelerated drug discovery, graph analytics, agentic workflows with a friendly face.

The repository has 11 stars and 2 forks, with the last commit 7 days ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/lynxkite/lynxkite-2000

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Lynxkite 2000

Powered by Claude · Grounded in docs

I know everything about Lynxkite 2000. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

Static checks derived from the repository 4 days ago. Heuristics on the source, not an audit.

  • ✓README presentThe repository ships documentation.
  • ✓License declaredUsable under a stated license.
  • ✓Tests presentA test suite exists in the repository.
  • ✓Dependencies pinnedA lockfile pins dependency versions.
  • ✓No dynamic code executionSource scan found no eval, dynamic Function, or shell execution.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

Releases

v0.3.0v0.3.0 · 25 Jan 2026This release focused on polishing the user interface. New Updated and added new boxes for using PyKEEN graph embeddings. #62 A UI refresh. Boxes have…
v0.2.1v0.2.1 · 4 Nov 2025Fixes an issue with loading workspaces. #81
v0.2.0v0.2.0 · 4 Nov 2025A big release with a lot of new features: Comments in workspaces. #7 Grouped boxes in workspaces. #10 Tables in "View tables" can be sorted. #18 Neural ODE and LSTM boxes in PyTorch models. #25 Dropdowns for some more parameters. #38…
v0.1.0v0.1.0 · 26 May 2025The first open-source release.

README

LynxKite 2000:MM

LynxKite 2000:MM is a GPU-accelerated data science platform and a general tool for collaboratively edited workflows.

Features include:

  • A web UI for building and executing data science workflows.
  • An extensive toolbox of graph analytics operations powered by NVIDIA RAPIDS and CUDA.
  • Life sciences tools, such as 2D and 3D molecule visualizations.
  • An integrated collaborative code editor makes it easy to add new operations.
  • An agentic assistant makes it easy to get started and add new operations without coding.
  • An environment for visually designing neural network model architectures.
  • The infrastructure for easily creating other workflow design environments. See lynxkite-pillow-example for a simple example.

Installation

pip install lynxkite

Getting started

License

LynxKite 2000:MM is licensed under the GNU AGPLv3. See the LICENSE file for details.

LynxKite Technologies offers a commercial license of LynxKite 2000:MM that includes additional features and support. Get in touch at lynxkite@lynxkite.com if you are interested in life sciences tools and cluster deployment!

README fetched from the repository 4 days ago. The original is authoritative.

Questions

About Lynxkite 2000

How do I install Lynxkite 2000?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Lynxkite 2000 safe to use with an AI agent?

Its trust score is 62 out of 100 (good). It passes 5 of the 6 static security checks run so far; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Lynxkite 2000 still maintained?

Yes — the last commit was 7 days ago. The repository has 11 stars and 2 forks and 42 open issues.