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.
-
Agentic toolkit for building and optimizing high-performance inference engines tailored to your GPU and desired LLM.
pypi Apache-2.0 ★ 48 -
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.
Apache-2.0 ★ 16 -
The all-in-one, airgapped Local AI. Ypipe bundles a high-performance inference engine, specialized models, and pre-configured MCP servers into a single, self-contained Java executable. Zero-dependency orchestration for autonomous agent workflows with 100% data sovereignty. No cloud, no Python hell - just industrial-grade local intelligence.
★ 14 -
Multi-backend GGUF vision-language inference engine (moondream3.1 · VideoChat3 · Qwen2.5-VL · MOSS-VL · VideoMAE/ViViT · SmolVLM) with a unified CLI, Web UI and an MCP server for agents.
NOASSERTION ★ 4 -
Reproducible scientific modeling engine and agent skill pack: versioned Model IR with explicit units, dimensional and numerical validation, calibration, sensitivity and uncertainty analysis, causal/Bayesian inference, and portable export via CLI, REST and MCP
pypi MIT -
Reverse Engineer any USB gadget: capture vendor-app traffic, infer the protocol with evidence, generate an open Python/libusb driver. CLI + MCP server.
pypi MIT ★ 17 -
tuningengines-cligithub.com/cerebrixos-org/tuning-engines-cliupdated this year
Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles p
npm MIT -
causal-panopticon-mcpgithub.com/apifyforge/causal-panopticon-mcpupdated this year
Causal Panopticon is a cross-domain causal discovery and inference engine for AI agents, exposed via the Model Context Protocol.
MIT ★ 1 -
tfmodsearchgithub.com/santyagoseaman/tfmodsearchupdated this year
TFModSearch — MCP server for AI agents (Claude Code, Codex, Claude Desktop) to search Terraform AWS modules with hybrid search engine combining semantic similarity (sentence-transformers), BM25 text relevance, and keyword matching. FastMCP-based, CPU-only inference.
pypi MIT License -
Meta-Forge Workshop: turn recurring work into governed AI workflow assets. MCP server + Claude Code plugin + dsh plugin — staged writes, evals-gated forging, inference engine. 元铸工坊 SOSOFAST:把最佳实践铸成可治理的 AI 工作流资产
AGPL-3.0 ★ 1 -
Context-Engine MCP - Agentic Context Compression Suite
MIT ★ 402 -
AI-Inference-Managed-by-AI: Go binary for managing AI inference on edge devices
Apache-2.0 ★ 19 -
AI Intelligence Platform -- knowledge graph + semantic search + reasoning + multi-agent debate in a single binary
NOASSERTION ★ 20 -
FastMCP server for the Animagine XL 4.0 image generation experience, providing prompt validation, optimization, explanation, img2img, and checkpoint/LoRA management tools. Works for any Stable Diffusion XL based model.
MIT ★ 1 -
irontology-mcpgithub.com/PromptExecution/irontology-mcpupdated this year
irontology - a memory safe rust Inference Runtime Ontology
-
Zikkarongithub.com/amanhij/Zikkaronupdated this year
Biologically-inspired persistent memory engine for Claude Code. 26 cognitive subsystems, Hopfield networks, predictive coding, causal discovery, successor representations, all running locally over SQLite.
MIT ★ 61 -
DIOgithub.com/nisaral/DIOactive
Drop-in OpenAI- and Ollama-compatible LLM gateway that learns each backend's latency online and routes vLLM / SGLang / TGI / Ollama with SLO-aware admission. No engine patches.
Apache-2.0 ★ 3 -
JEV and local LAYA for MCP. Typed decisions, bounded inference and durable decision records.
Apache-2.0 ★ 1 -
Fleet control plane: probe, boot and recover multi-node AI subsystems with proof. Docker and self-hosted inference fleet management.
MIT -
Local MCP context server for AI agents: persistent memory, sourced knowledge graphs, full-text search, and rule-based inference with SQLite and clingo.
-
Aurora MCP server — glass-box statistical analysis for AI agents: 19 research-grade methods, cited findings, integrity-hashed bundles, zero invented numbers. Now with a calibration engine: measured false-fire rates attached to changepoint findings, verdicts downgraded when the data can't support the claim. Local-first.
pypi Apache-2.0