The open computational chemistry engine AI agents call to do real discovery.
Cheminformatics, GPU simulation, and quantum chemistry through one MCP + REST surface. Any MCP-compatible AI assistant, any LLM. Install locally, self-host, or route regulatory work through the FAVES compliance API.
$ git clone https://github.com/NovoMCP/novomcp \
&& cd novomcp/orchestrator \
&& pip install -r requirements.txt \
&& python main_https.pyContainers work too. docker compose up in the repo root does the same.
Bringing one drug to approval costs about $2.6 billion, and roughly one in twenty survives. NovoMCP moves the decision in silico, before the spend.
license
the catalog
zero wiring
(Novo + Compute)
supported
jurisdictions
Models are interchangeable. The engine they run on is not.
NovoMCP holds the 69-tool catalog, the NovoExpert ADMET and clinical-outcome models, the FAVES compliance layer, the immutable audit trail, and cross-run memory. The model is free to replace. The engine underneath carries the value.
One chemistry engine. One simulation engine.
Novo exposes cheminformatics + validated ADMET + compliance. Novo Compute runs the physics when a question needs it. Together they let an assistant think, test, and learn about molecules through a single MCP-compatible surface.
The chemistry engine
Cheminformatics, ADMET, compliance, target evidence, and discovery orchestration. Install the open engine and reach all of it through one MCP server, from any MCP-compatible AI assistant.
- →RDKit properties, similarity, and structural alerts in-process
- →NovoExpert ADMET and clinical-outcome models
- →FAVES compliance at the point of decision
- →11-stage autonomous discovery funnel
The simulation engine
GPU and quantum chemistry for the questions that need real physics. Ships in the same open engine. The compute tools appear alongside Novo once the optional GPU services are wired.
- →AutoDock-GPU docking with strain correction
- →GROMACS molecular dynamics
- →xTB, CREST, and neural-network potentials
- →OpenFold3 structure prediction
The scientific method, run end to end.
One instruction starts an eleven-stage discovery funnel. Targets are found and validated, the literature read, actives pulled, candidates profiled, optimized, docked, gated on a calibrated clinical-clearance estimate, carried through molecular dynamics, and closed out with patient stratification against pharmacogenomic evidence.
Every stage writes to an immutable audit trail. Cross-run memory carries what prior runs learned into the next.
How AgentMode worksDepth in the fields chemistry decides.
Not a claim to every industry. Four domains where the tools already ship and the accuracy is benchmarked.
Drug discovery narrows millions to one candidate through an eleven-stage funnel. Materials work stays a flexible toolkit. Four workflows, no forced pipeline. One engine underneath both: xTB, CREST, NNPs, FEP, reaction thermodynamics, transition states. Same physics, two shapes.
Every decision is on the record.
Every decision the AI makes is written to an immutable audit trail. Any funnel reconstructs completely: what was tried, what was rejected, why, and who approved it.
Observability is built into the engine from the first stage. It is the first question every enterprise buyer asks.
Immutable audit trail
Per-stage logging across the full discovery funnel. Reproducible, reconstructable, exportable.
FAVES V4 compliance
1,585 SMARTS across 8 jurisdictions. Runs inline at the point of decision, ahead of any terminal gate.
Cross-run memory
Funnel context persists across sessions. The engine remembers what prior runs learned.
Agent governance
RFC 8693 token exchange, per-agent key scoping, and agent-level audit on Enterprise.
Numbers you can check.
Every figure here is measured and traceable to a public source: a benchmark run on a single GPU, a preprint, or the CI that runs on every fresh clone. Nothing rounded up, nothing unsourced.
GROMACS · one A10G
AutoDock-GPU
GFN2-xTB
five predetermined tests
benchmarked on public TDC
GFN2-xTB
Sources: speed figures measured on a single NVIDIA A10G (10 ns MD benchmark). FAVES validation: FAVES V4 preprint (chemRxiv). ADMET benchmarked against the Therapeutics Data Commons . NovoMCP’s own models on a public suite, no leaderboard claim.
The work, published.
Outcome-level methods and benchmarks, in the open.
From the newsroom.
The next discovery runs on an engine you can inspect.
Install the engine on your own hardware, or route regulated compliance work through the hosted FAVES API. Same engine underneath.