qcoscloud

The customer SDK, CLI and MCP server for SoftQuantus compute — one prepaid wallet across QPU (via QCOS), on-demand GPU (via Softquantus Cloud), and free simulation. The platform Execution Plane authorizes, meters and settles every call; this client never touches a cloud or a credential.

pip install qcoscloud            # SDK + CLI
pip install "qcoscloud[mcp]"     # + the MCP server for AI agents
export QCOSCLOUD_API_KEY=sq-live-…    # create one in the console → API Keys

SDK

from qcoscloud import QCOSCloud
qc = QCOSCloud()                                  # reads QCOSCLOUD_API_KEY
qc.credits()                                      # prepaid balance (USD)
bell = """OPENQASM 2.0;
include "qelib1.inc";
qreg q[2]; creg c[2];
h q[0]; cx q[0],q[1]; measure q -> c;
"""
qc.simulate(qasm=bell, shots=1000)                 # FREE test simulation
qc.run("ionq.qpu.aria-1", qasm=bell, shots=2000, instance="research")
qc.gpu_job(gpu="a100-80gb", command="python train.py", minutes=30)  # GPU
qc.workload(job_id)                               # status + cost

CLI

qcoscloud credits
qcoscloud computers
qcoscloud instances create research --plan prepaid --qpus ionq.qpu.aria-1
qcoscloud simulate --qasm bell.qasm --shots 1000
qcoscloud run --target ionq.qpu.aria-1 --qasm bell.qasm --shots 2000 --instance research
qcoscloud gpu --type a100-80gb --command "python train.py" --minutes 30
qcoscloud workloads

MCP (for AI agents — the SynapseX Lab, Claude Desktop, Cursor)

python -m qcoscloud.mcp_server        # stdio MCP server

Exposes 12 tools: get_credits, list_computers, list_instances, create_instance, list_targets, run_simulation, run_qpu_job, run_gpu_job, run_cpu_job, get_workload, get_evidence, and cancel_workload. An AI can drive compute safely — every run is metered against the same wallet with the same cost guardrails.

See docs/COMPUTE_INTEGRATION.md (full integration) and docs/LAB_AI_INSTRUCTIONS.md (desktop lab + AI instructions).

Cost safety

Runs reserve their worst-case cost before provisioning, so you can never overspend; GPU is stopped/deprovisioned when its reservation is exhausted; the free plan runs simulators at $0. Errors carry a machine reason (insufficient_credits, runtime_bound_required, free_plan_limit_met, …) and a human hint.