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.
-
A production-grade, MCP-compliant agentic forecasting tool. Designed for Agentic AI orchestrators to autonomously resolve inventory shortages, evaluate demand risk, and execute quantile-bounded supply-chain decisions—without requiring local fine-tuning.
MIT -
faim-mcpgithub.com/S-FM/faim-mcpupdated this year
MCP server for zero-shot time-series forecasting
npm ★ 8 -
Zero-shot AI-text detection that runs on your own computer. 80.08% on the official RAID test, ahead of Binoculars. Web app, CLI, API, MCP server.
★ 1 -
A prediction and forecasting harness for supply chain operations. Connect a table, pick a model, read the signs. Zero-shot models behind one interface, exposed as an MCP server.
Apache-2.0 -
Zero-shot decision model on DiffusionGemma: policy templates answered in one forward pass, with a probability for every option, a hesitation score and per-policy calibration. CLI, MCP server, HTTP gateway and web Studio.
Apache-2.0 ★ 10 -
An MCP server exposing local embedding tools - semantic search, comparison, clustering and zero-shot classification - so an agent can call them in a loop without an API round trip. Caching the embeddings took a search from 1040ms to 1.2ms. PyTorch, sentence-transformers, MCP Python SDK v2.
MIT -
Sovereign local-first AI voice studio. Neural speech synthesis, zero-shot voice cloning, zero-latency dictation, and MCP agent voice I/O. Built with Tauri & FastAPI.
AGPL-3.0 -
Zero-clone MCP server for 200k+ ATP matches (1968-2026), Match Charting Project shot/rally profiles, H2H, GSDI & NBI.
pypi NOASSERTION -
Title and abstract screening for systematic reviews: zero-shot LLM classifier ranking with a statistical stopping criterion. Web version, Python package and MCP server.
Apache-2.0 -
LLM agent that triages GitHub issues (type labels, duplicates) through its own MCP server, benchmarked on 120 real astral-sh/uv issues: zero-shot vs RAG vs agent.
MIT -
depth-pro-dockergithub.com/neosun100/depth-pro-dockerupdated this year
Production-ready Docker deployment for Apple's Depth Pro model - Zero-shot monocular metric depth estimation with Web UI, REST API, and MCP Server
NOASSERTION ★ 2 -
higgs-audio-webgithub.com/neosun100/higgs-audio-webupdated this year
🎵 All-in-One Docker deployment for Higgs Audio v2 with Web UI, REST API & MCP support. Features: Expressive TTS, Zero-Shot Voice Cloning, Multi-Speaker Dialog, Text Profile Voice.
Apache-2.0 ★ 3 -
Agentic-Multimodal-Expense-Processinggithub.com/uditsanghvi07/Agentic-Multimodal-Expense-Processingupdated this year
Agentic Multimodal Expense Processing (AMEP): End-to-end GenAI pipeline using Multimodal LLMs for zero-shot data extraction from invoice images. Implements an Agentic MCP server for autonomous classification, transforming unstructured documents into structured expense reports in real-time Google Sheets for analytics.
-
Zero-shot forecasting, tabular classification, and regression via MCP — exposes Google TimesFM 2.5 and TabFM v1.0.0 to AI assistants. Just attach a CSV and describe what you want to predict.
Apache-2.0 ★ 32 -
Local GPU text-to-speech for AI agents via MCP - Chatterbox turbo/nano/multilingual, zero-shot voice cloning, resident worker with sentence batching, and a local web panel for worker control, model state, speak, replay and stop.
MIT ★ 2 -
Self-hosted audio API in one Docker container. Stem separation, mastering, MIR (BPM/key/chords), audio→MIDI, text-to-music + SFX (MusicGen/Stable Audio/Riffusion/AudioLDM2), diarization, speech enhancement, restoration, embeddings + zero-shot tagging, workflows, async + webhooks. REST + MCP. CPU + CUDA.
oci WTFPL ★ 6 -
ಎಲ್ಲಿದೆ — where is what I shot? A free, local tool that indexes the photos and videos scattered across your drives and makes them searchable by what is in them. Runs on your machine as an MCP server. Nothing is uploaded.
MIT -
Local-first AI resume tailoring engine with deterministic zero-token fact verification, MCP server integration, and sub-30ms Typst WASM PDF compilation. No hallucinations, altered metrics, or broken formatting.
npm MIT ★ 2 -
MCP server for Jevx (jevx.org) — run Jev AI typed decisions (choice, score, noul with probabilities) from any MCP client, on your own Jevx API key.
npm MIT -
mcp_coordinatorgithub.com/angrysky56/mcp_coordinatorupdated this year
The MCP Coordinator is a self-optimizing orchestrator that bridges the gap between high-level human intent and low-level system execution. It is characterized by its ability to learn (skills), scale (recursion), adapt (discovery), and reflect (RAA).
NOASSERTION ★ 2 -
ctt-shellgithub.com/MauricioPerera/ctt-shellupdated this year
Universal AI agent framework — 1B models compose multi-step plans like 12B with structured context (CTT). 6 domains, 8 MCP tools, 167 tests, zero runtime deps.