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.
-
⚡ Ultra-fast O(1) Active Inference & Bayesian Cognitive Governor for AI Agents (Antigravity, Claude, Cursor) & Embedded Systems. Zero-alloc C11 core (<36KB) + FastMCP server.
MIT ★ 5 -
Autonomous AI-driven Root Cause Analysis (RCA) & causal inference engine for EV fast-charging networks. Triages multi-party telemetry across OCPP 1.6-J and OCPI roaming protocols with FastMCP agentic diagnostics.
MIT ★ 1 -
High-performance MCP for generating images using DALL·E 3 – optimized for fast, scalable, and customizable inference workflows.
npm MIT ★ 1 -
coral-tpu-mcpgithub.com/marc-shade/coral-tpu-mcpupdated this year
Coral TPU MCP Server - Fast local ML inference for agentic systems
★ 1 -
⚡ 100% offline, zero-cost drop-in alternative to TypeSafe Jev System One decision models in Rust (<18ms on CPU)
MIT ★ 11 -
claude-lfr-mcphttps://gitlab.com/derico/claude-lfr-mcpupdated this year
Fast CPU-based RAG for codebases using BGE embeddings and Qdrant. MCP server for Claude Code.
pypi MIT -
VelociRAGgithub.com/HaseebKhalid1507/VelociRAGupdated this year
Lightning-fast RAG for AI agents. ONNX-powered, 4-layer fusion, MCP server. No PyTorch.
pypi MIT ★ 12