Skip to content

NovoMCP

The open computational chemistry engine for drug discovery and materials science.

NovoMCP is an agent-callable engine that exposes molecular intelligence, cheminformatics, ADMET prediction, molecular docking, molecular dynamics, quantum-mechanical calculations, protein structure prediction, and a governed discovery funnel through the Model Context Protocol and a curated REST API.

One engine. Two domains. Four surfaces.

Get started

What it does

  • 11 tools work fully local out of a 67-tool catalog. The rest unlock as you deploy compute services, provide your own data, or subscribe to hosted APIs. See Tool availability for the full map.
  • Full 67-tool catalog spans cheminformatics (properties, similarity, filtering), ADMET prediction, docking, molecular dynamics, protein structure prediction, quantum-mechanical calculations, literature/patent search, regulatory compliance
  • REST API with a curated OpenAPI 3.1 spec at /v1/openapi.json
  • MCP JSON-RPC at /mcp/ — usable from any MCP-compatible client (Claude Desktop, Cursor, Codex, Zed, Cline, and others)
  • Autonomous discovery funnel — trigger with "Novo AG" or "agm" from any MCP client, returns an 11-stage protocol for the LLM to execute
  • Pluggable everything — auth (AuthGate), metering (CreditMeter), audit (AuditSink), LLM providers (OpenAI, Anthropic, Ollama, Azure) all swap via env vars

What lives elsewhere

By design, the following ship separately:

  • FAVES certified hosted API — the operational commitments (SLA, audit-log retention, drift monitoring, IQ/OQ/PQ) that a regulated submission needs, delivered as a paid service at api.novomcp.com. The V4 framework paper is published on Zenodo under CC-BY-NC-ND 4.0. The open reference implementation of the framework ships in this OSS release as the faves-compliance Docker image — run locally for triage, route the shortlist through the hosted API when you need the certified record-of-audit.
  • Curated 122M-molecule enriched corpus — publishing to AWS Open Data / Kaggle / Zenodo as a downloadable dataset. Cached lookups happen through the FAVES compliance service when configured.
  • Trained clinical outcomes model weights — NovoExpert-3, separate license.

None of these are required for the engine to run.

Licensing

  • Top-level tree (surfaces, wrappers, connectors, protocol docs): Apache-2.0 (LICENSE)
  • Orchestration core (orchestrator/mcp/): Business Source License 1.1 with a change date of 2029-07-12 to Apache-2.0 (LICENSE.core). Non-production use, self-hosting, and modification are permitted immediately.
  • Pre-trained model weights in companion repositories: MIT.

Contributing

  • Issues + PRs welcome on the public repo. See CONTRIBUTING.md for the workflow.
  • Discussions: use GitHub Discussions for questions and design conversations.
  • Support: best-effort. NovoMCP is a reference-quality open-source project; there is no support commitment.

Reading further