Skip to content
Open source · Apache-2.0

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.

Install
$ git clone https://github.com/NovoMCP/novomcp \
    && cd novomcp/orchestrator \
    && pip install -r requirements.txt \
    && python main_https.py

Prefer containers? docker compose up in the repo root also works.

Scroll
Where the decision happens decides what it costs

Bringing one drug to approval costs about $2.6 billion, and roughly one in twenty survives. We move the decision in silico, before the spend.

Apache-2.0
the
license
68
tools in
the catalog
11
work with
zero wiring
2
MCP servers
(Novo + Compute)
4
LLM providers
supported
8
FAVES
jurisdictions
Why an engine
Models are interchangeable. The engine they run on is not.

Remove the model and you swap one assistant for another. Remove NovoMCP and you lose the 67-tool catalog, the ADMET and clinical-outcome models, the FAVES compliance layer, the immutable audit trail, and cross-run memory. When the model is free to replace and the engine underneath is not, the engine is where the value lives.

The platform

One intelligence layer. 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.

Novo

The intelligence layer

localhost:8018/mcp

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
Novo Compute

The simulation engine

same endpoint, GPU wired

GPU and quantum chemistry for the questions that need real physics. Ships in the same open engine — the compute tools show up alongside Novo once you wire the optional GPU services.

  • AutoDock-GPU docking with strain correction
  • GROMACS molecular dynamics
  • xTB, CREST, and neural-network potentials
  • OpenFold3 structure prediction
any MCP-compatible assistant
you Profile this scaffold for ADMET and compliance, then dock the clean candidates against the target.
resolved 4 analogs · ran batch_profile across 84 properties
flagged 1 PAINS alert via check_compliance (FAVES)
docked 3 survivors with dock_with_strain · top pose −9.4 kcal/mol
every step written to the immutable audit log
AgentMode

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 works
Governance

Before you govern it, you can see it.

Every decision the AI makes is written to an immutable audit trail. You can reconstruct any funnel: what was tried, what was rejected, why, and who approved it.

Observability is not bolted on after the fact. It is built into the engine, and 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, not as a 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.

Open source · Apache-2.0

The next discovery runs on an engine you can trust.

Install the engine on your own hardware, or route regulated compliance work through the hosted FAVES API. Same engine underneath.