cuOpt is NVIDIA's GPU-accelerated optimization solver for LP, MILP and QP (beta), and it is offered through a Python API, a C API and a CLI 1. The indexed cuopt-numerical-optimization-api skill covers the Python and C routes for solving these problem classes 1. No other source in the set is a competing solver, so alternatives are not listed.
- 1
cuOpt (NVIDIA)nvidia.comverified and signed
Solves LP, MILP and QP (beta) problems via its Python API, C API and CLI, with the cuopt-numerical-optimization-api action covering all three 1.
official:MCP server · NVIDIA CUDA Docs+84 community tools built for it
for agents: cuopt-numerical-optimization-api · cuopt-numerical-optimization-api-c · cuopt-numerical-optimization-api-python
Sources
- 1Brev.dev Consolebrev.nvidia.com · read 2026-10-29
For agents: the 10 actions behind this answer
cuopt-numerical-optimization-api · cuopt-numerical-optimization-api verified and signed
LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.
arize-prompt-optimization · arize-prompt-optimization verified and signed
Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond bette
optimize · olive found in code, not yet checked
Optimize a model end-to-end. Returns a job_id — use get_job_status() to poll progress.
API · looker-sdk verified and signed
custom_api_call · OpenAI (Activepieces) verified and signed
Custom API Call — Make a custom API call to a specific endpoint
update_instance_vector_optimization · Neo4j MCP Clients & Servers found in code, not yet checked
Update the vector optimization setting of a Neo4j Aura instance.
api · ghapi verified and signed
gke-cost-optimization · gke-cost-optimization verified and signed
Optimizes GKE costs, rightsizes workloads, and configures Spot VMs, CUDs, cost allocation, and resource quotas. Use when optimizing GKE cluster or workload costs, configuring GKE cost allocation or quotas, rightsizing CPU/memory requests, or selecting Spot VMs and machine types. Don't use for genera
agents-optimize · agents-optimize verified and signed
Use when measuring or improving agent quality and performance — set up evaluators, online monitoring, CI/CD quality gates, observability, or cost optimization. Triggers on: "evaluate my agent", "add evaluator", "measure quality", "quality gate", "run evals", "agent too slow", "why is it slow", "redu
onramps-plan · Cloudflare API verified and signed
Plan On-ramp
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.