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.
-
Self-tuning, disposable Docker sandboxes for AI agents. Runs code in locked-down containers sized to your hardware, with GPU sharing, crash cleanup, a CLI, a Python API and an MCP server for Claude.
MIT -
MCP server that lets AI agents share one NVIDIA GPU — cross-session model claims, real busy detection via NVML, protected eviction, and full VRAM visibility for Ollama + everything else holding memory
MIT ★ 1 -
Local knowledge search for coding agents: GPU hybrid search and reranking with source citations, plus saved decisions and session captures, served by one shared MCP daemon.
MIT ★ 1 -
Local, offline web studio for game, video, podcast and social assets: images, 3D models, SFX, music and voices from ~100 open-weight models. Shared asset library, single-GPU job queue, prompt improver, commercial-licence filter, loudness-matched export presets and a built-in MCP server.
Apache-2.0 -
BitPull (bitpull.cloud): share signed, AI-readable code, computing power and open AI models with AI tools through MCP. CLI and MCP server.
npm UNLICENSED