MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Persistent GPU jobs for AI agents. MCP + CLI, hardware-aware scheduling, Kaggle adapter, and recoverable artifacts for Codex and Claude Code.
MIT ★ 21 -
FIREFIGHTER: the coordinator and scheduler for unmanaged AI agents. Your AI agents won't set your GPU on fire. Or your CPU, your RAM, or your network. Claude Code, Codex, Gemini, Cursor, Kimi and more; MCP server; Windows/macOS/Linux.
MIT -
Open-source Kubernetes FinOps operator: cost per namespace, team, GPU and LLM token, schedules that scale idle environments and cloud databases to zero, budgets, chargeback and right-sizing with a rollback guard. Helm chart, dashboard, REST API, MCP server.
Apache-2.0 ★ 7 -
Cooperative GPU queue for people and AI agents: one line per card, heartbeats, polite yields, MCP server. Home on Codeberg.
MIT -
MCP server that lets Claude Code sessions lease CPU and GPU capacity from Allot
cargo MIT OR Apache-2.0 -
Self-hostable GPU-aware job broker for your own machines, with native MCP/agent integration
pypi MIT ★ 6 -
gpubrokergithub.com/wudaming00/gpubrokerupdated this year
Lightweight GPU resource broker for multi-project single-host ML workloads. HTTP API + Python client + MCP server for AI agents.
NOASSERTION -
Local resource-aware task queue (daemon, CLI, web UI, MCP) — YAML jobs with CPU/RAM/GPU admission
pypi MIT -
Train PyTorch on every GPU you can reach: one Trainer, from your laptop to many machines. NVIDIA CUDA, Apple Metal and CPU; self-hosted, open source.
pypi Apache-2.0