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.
-
The SQLite of Vector Search & Episodic Memory for AI Agents in ~120KB. Pure C99, AVX2+FMA, ARM NEON, FASM x64, Native MCP Server.
MIT ★ 7 -
CPU-only LLM inference engine in pure Rust — 4-bit quantized models, hand-written AVX2 kernels, speculative decoding, and a local HTTP/MCP server. No GPU, no Python runtime.
cargo Apache-2.0 ★ 16 -
Ultra-fast cross-platform parallel code & symbol search engine in pure C (AVX2 & ARM NEON SIMD) with built-in MCP 2.0 server, code outlines, and ripgrep/fd compatibility for AI coding agents.
MIT ★ 1 -
vmafxgithub.com/VMAFx/vmafxactive
VMAFx: perceptual video quality assessment (VMAF), GPU-accelerated and SIMD-tuned. CUDA, SYCL, HIP and Metal backends checked against the CPU scores, AVX2/AVX-512/NEON, tiny-AI models, an MCP server, Kubernetes/Helm deployment. Fork of Netflix/vmaf; fork code EUPL-1.2, Netflix code BSD-2-Clause-Patent.
EUPL-1.2 ★ 7 -
Enterprise Document Intelligence Platform with High-Performance C++ Extensions, API v2, MCP, and Vector Search
pypi MIT -
High-performance native cognitive memory engine (.ame) for AI Agents with fused vector-graph search, sub-millisecond mutations & MCP server