The engine, as an API.
Call any of Novo's 69 in-silico tools over HTTP — from a script or your own AI agent. One base URL, one Bearer key, usage-based credits. The same engine behind the MCP connectors, exposed directly to your code.
One pattern for all 69 tools.
Every tool is POST /v1/tools/{name} with a JSON body and a Bearer key. No SDK required — it's just HTTP.
curl -s https://api.novomcp.com/v1/tools/validate_target \
-H "Authorization: Bearer $NOVOMCP_API_KEY" \
-H "Content-Type: application/json" \
-d '{"arguments": {"target": "EGFR", "disease": "lung cancer"}}'Responses come back as { result, usage } — the tool's payload plus the credits spent and your remaining balance. Full curl, Python, and JavaScript examples are in the API docs.
Bring your own AI agent.
NovoMCP is the engine, not the reasoner — you supply the model. Expose Novo's tools to your own agent (Claude API, GPT, anything) and let it call them in its loop, with live tool schemas from GET /v1/tools.
# Expose Novo's tools to your own model and let it call them in its loop.
def call_novomcp(tool, arguments):
r = requests.post(
f"https://api.novomcp.com/v1/tools/{tool}",
headers={"Authorization": f"Bearer {KEY}"},
json={"arguments": arguments},
)
return r.json() # { "result": {...}, "usage": {...} }Which door is which.
api. is the one REST API you call from your code. ai. and compute. are the MCP connectors you add to an assistant. app. is the dashboard. Same account and credits across all of them.
api.novomcp.comThe REST API — call tools from your own code or agentthis pageai.novomcp.comMCP connector — Novo (core), added inside an AI assistantMCPcompute.novomcp.comMCP connector — Novo Compute (paid), added inside an assistantMCPapp.novomcp.comDashboard — create keys, watch usage and billingkeysWire 69 in-silico tools into your stack.
Create a key in the dashboard, then call the engine from anywhere. Compute tools (docking, MD, FEP, QM) require a paid plan.