- Ruv Swarm @ruvnet/ruv-swarmNeural network swarm orchestration with WebAssembly acceleration and MCP integration6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.381 GitHub stars.
- AISIX AI Gateway @api7/aisixSelf-hosted AI gateway that governs MCP servers, LLM traffic, and A2A agents behind one endpoint3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.184 GitHub stars.
- Evalview @hidai25/evalview-mcpRegression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.137 GitHub stars.
- freellmpool @0xzr/freellmpoolOpenAI-compatible MCP gateway cataloging 22 LLM providers, with routing, failover, and tools.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.122 GitHub stars.
- SAS Viya @sassoftware/sas-mcp-serverExecute SAS code and query Compute, CAS, and model APIs on SAS Viya via OAuth 2.0.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.64 GitHub stars.
- ZenML @zenml-io/mcp-zenmlMCP server for discovering, reading, and changing ZenML resources with compact generic tools3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.49 GitHub stars.
- WaveSpeed MCP @wavespeed/mcpRun any model on the live WaveSpeed catalog: image, video, audio, 3D.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.34 GitHub stars.
- Replicate @mcparmory/replicateRun AI models, create deployments, and manage predictions via cloud API6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.32 GitHub stars.
- Jev-Style @lawrence3699/jev-styleLocal 2B and 0.8B decision models: calibrated yes/no, choice and score answers for your agent.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.16 GitHub stars.
- RAGScore @hzyai/ragscoreGenerate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.15 GitHub stars.
- AutoCarver @mdefrance/autocarverQualify dataset columns and process them against a target with AutoCarver, fully on your machine.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.11 GitHub stars.
- Ultralytics Platform MCP @amanharshx/ultralytics-mcpMCP server for Ultralytics Platform projects, datasets, training, prediction, exports, and models.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.10 GitHub stars.
- Vmanomaly @victoriametrics-community/mcp-vmanomalyMCP Server for vmanomaly - VictoriaMetrics anomaly detection3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.10 GitHub stars.
- Colab Exec @pdwi2020/mcp-server-colab-execExecute Python code on Google Colab GPU runtimes (T4/L4) from any MCP client9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.9 GitHub stars.
- Vmanomaly @victoriametrics/mcp-vmanomalyMCP Server for vmanomaly - VictoriaMetrics anomaly detection3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.9 GitHub stars.
- Metrillm @metrillm/metrillmBenchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.8 GitHub stars.
- Tuning Engines - Governed AI Runtime @cerebrixos-org/tuning-enginesGovern model, agent, skill, and MCP workflows with policy, approvals, traces, and usage analytics.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Talkies @psyb0t/talkiesSelf-hosted MCP server for speech: ASR transcription, TTS synthesis, and file staging tools.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.5 GitHub stars.
- Replicate @sena-labs/replicate-mcp-serverReplicate MCP server - image, video, audio, speech, LLM, vision, upscale, 3D, training. 36 tools.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
- Clef @highlyloadedego/clef-mcpLocal MCP server for the Cloudflare Clef-Flash decision model: structured decisions, fully offline4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Neural @andylbrummer/neural-mcpGPU-accelerated MCP server for neural network training, deep learning, and model experimentation4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
Machine learning MCP servers
A server here trains, fine-tunes, evaluates or hosts machine learning models.
Not here: servers that merely use AI to do something else.
239 remote224 localTagged by Odel's AI, which can make mistakes
Most popular in Machine learning
By GitHub stars, at most two per publisher- Number 1: FunASR@modelscope/funasr-mcpTranscribe local audio with FunASR and SenseVoice using private, on-device inference.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.20,637 GitHub stars.
- Number 2: AutoTS@winedarksea/autotsAutomated time series forecasting with model search, anomaly detection, and event risk analysis3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1,430 GitHub stars.
- Number 3: GoModel@enterpilot/gomodelSelf-hosted gateway aggregating upstream MCP servers behind one authenticated HTTP endpoint.15% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1,228 GitHub stars.
