Who it is for
Researchers in drug discovery and materials science working with simulation models.
AI Connectors · Healthcare & Life Sciences
Physics-based quantitative models for drug and materials research
Overview
SandboxAQ's Large Quantitative Models combine physics-based simulation with machine learning, and are aimed at drug discovery and materials innovation. This connector puts them behind natural language, so a researcher states a hypothesis instead of configuring a simulation.
The claim in the listing is about access rather than capability: models of this kind normally sit behind specialist tooling, and the connector is the layer that removes that step. No endpoint is published in the directory listing. This connector carries the partner tier, meaning it passed a review step, and SandboxAQ publishes documentation.
Researchers in drug discovery and materials science working with simulation models.
The listing publishes no endpoint URL, so there was nothing to connect to and seven is SandboxAQ's own count. The listing describes access to Large Quantitative Models rather than individual calls.
Availability
SandboxAQ is listed in the Claude connectors directory only. SandboxAQ has no app under the same domain in the ChatGPT directory; 392 of the 3,150 products here are on both marketplaces, and this is not one of them.
The MCP server behind a Claude connector is usually the same server a ChatGPT app would need, so the absence is a distribution decision rather than a technical one.
Claude listing
SandboxAQ publishes 7 tools to Claude. That is a mid-sized surface: 33.4% of the 1,253 Claude-listed connectors expose fewer.
The median Claude-listed connector filed under Healthcare & Life Sciences publishes 6, so this one runs one tool above its bucket's median and ranks 19th of 51 by tool count.
It falls in the 7-10 tools band, which holds 14.6% of the Claude directory.
SandboxAQ's Claude listing does not publish an endpoint URL. 48 of the 1,253 Claude listings are in the same position: real listings with documentation but no URL in the directory record, so the endpoint has to come from the publisher's own docs.
Every connector in the Claude directory is remote, all 1,253 of them, so transport is not a differentiator there.
SandboxAQ carries partner verification in the Claude directory, which 474 of 1,253 listings do (37.8%). That is a review step past self-publishing, not an Anthropic-built server.
In the publisher's words
SandboxAQ's Large Quantitative Models (LQMs) combine physics-based simulation with machine learning to accelerate drug discovery and materials innovation. Now, LQMs are accessible through large language models. Researchers can access frontier scientific AI in natural language, moving faster from hypothesis to breakthrough.
Quoted from the connector's own Claude directory listing as captured in August 2026. Node8 did not write it and does not vouch for it.
Nearby
LogD and pKa predictions for early compound triage
Claude
Benchling research data through its own scientific AI chat
Claude
Scientific figure templates and icons for research visuals
Claude · ChatGPT
Literature search and structured reports across papers
Claude · ChatGPT
Discover Synapse research datasets and read their metadata
Claude
Computational biology jobs run from chat
Claude · ChatGPT
This is an independent catalogue entry compiled by Node8 from SandboxAQ's public marketplace listing as it stood in August 2026. Listing facts come from the marketplaces; the comparisons against the rest of the directory and any live-endpoint measurements are Node8's. Node8 is not affiliated with SandboxAQ, and inclusion here is not an endorsement.
Node8 builds MCP servers end to end: deciding which tools are worth exposing, the authentication and permission model, the review submissions, and the onboarding that gets them used. One server serves ChatGPT, Claude, and Microsoft Copilot.