AI and Machine Learning MCP servers

Top 100 by trust score Trust score 0–100

• LLMIntel Model Lifecycle

  Check whether an LLM model id is deprecated, retiring, or retired, and what to migrate to.

  remote · npm 96

• Genudo

  Build & manage Genudo AI agents for any messaging channel — pipelines, integrations, knowledge.

  npm 96

• StackMap

  Search 344 human-reviewed AI/agent repos and the 817 typed connections between them.

  npm 96

• io.github.SunrisesIllNeverSee/tteop-mcp

  Build, validate, and describe TTEOP telemetry envelopes for AI operator token efficiency.

  npm 96

• freellmpool

  OpenAI-compatible MCP gateway cataloging 22 LLM providers, with routing, failover, and tools.

  pypi 95

• io.github.gabrielmahia/offline-mcp

  MCP server enabling offline-first agent operation over intermittent connectivity

  pypi 95

• io.github.JoaoBerne/cli-bridge-mcp

  Other AI CLIs (Gemini, GPT, Claude, opencode, Ollama) as a council — ban-safe, no API keys.

  pypi 95

• ai.voxell/forge

  MCP server for Forge, Voxell's embedding API. Voxell's Ingot-8B-R3 ranks #1 for English on MTEB.

  npm 94

• Promptibus MCP

  Model intelligence for AI agents — syntax, params, pricing for 67+ generative AI models.

  npm 94

• io.github.Filip-Pajalic/tensorcad

  Design transformer LLM architectures and report their parameters, FLOPs, memory and cost

  npm 94

• io.github.jeff-atriumn/tokencost-dev

  LLM pricing oracle — model lookup, cost estimation, and comparison via LiteLLM

  npm 94

• io.github.MetriLLM/metrillm

  Benchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client

  npm 94

• io.github.skill-federation/skillfed-mcp

  Find vetted agent skills for your task — privacy-preserving skill discovery over MCP.

  npm 94

• ~alter mcp-ollama

  Wraps local Ollama models so bulk generation runs on your own hardware, not a paid API.

  npm 94

• inference.sh

  run any ai model. compose agents, stack knowledge, connect tools. one api, pay per run.

  remote 93

• Perspect

  Convene a panel of expert AI personas to debate any decision from every side.

  remote 93

• OpenClaw MCP Server

  MCP server bridging Claude.ai/Desktop with self-hosted OpenClaw via OAuth 2.1.

  npm · oci 93

• Cheaplane

  Offload grunt work from your premium agent to cheap models — auto-routing and billing isolation.

  pypi 93

• African Speech Corpora Quality Audit

  Read-only, provenance-aware selection of Wolof speech corpora by measured quality.

  pypi 93

• Strategic Agent Reasoning MCP

  Strategic BDI reasoning engine for autonomous AI agents with spatial utility and replanning.

  npm 93

• Behavior Runtime MCP

  In-browser ~60Hz behavior tree execution engine with reactive triggers and blackboard projection.

  npm 93

• Qiskit MCP Server

  MCP server for Qiskit quantum computing with circuit serialization utilities

  pypi 93

• SpeechWeave

  Transcribe local files and URLs with SpeechWeave's OpenAI-compatible Speech-to-Text API.

  npm 93

• ModelShortlist

  Local BYOK MCP for AI model shortlisting using OpenRouter + Artificial Analysis.

  npm 92

• DecimalAI Skills Registry

  Search agent skills ranked by measured lift vs a no-skill baseline, with safety and rankings.

  pypi 92

• Verlon AI MCP

  Inspect and manage Verlon AI gates, logs, recommendations, and experiments from any MCP client.

  npm 92

• Bay Run

  Free OpenAI-compatible inference with signed provenance receipts and 3 focused MCP tools.

  remote 92

• io.github.Craig-Horton/aibvf-mcp

  AI BVF: review AI proposals with Stop, Fix or Accelerate, evidence gaps and next actions.

  npm 92

• io.github.Davmunrey/trazum

  Trazum as an MCP server: let an agent price and budget its own prompts before it sends them.

  npm 92

• TokenLab MCP Server

  TokenLab MCP server: 32 default and 89 full-profile tools for models, media, tasks, and files.

  npm 92

• ToolRouter

  The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.

  remote 92

• io.github.omkar9854/token_optimizer

  Reversible context compression for AI agents: cut token usage up to 94%, originals retrievable

  pypi 92

• io.github.rotifer-protocol/mcp-server

  Search, compare, and install self-evolving AI Agent Genes ranked by Arena fitness

  npm 92

• io.github.RyanAlberts/agent-harnesses

  Agent-harness picks, decision guides, setup templates, and skills; live GitHub/HN discovery.

  pypi 92

• io.github.smurfy92/openclaw-control-mcp

  MCP server bridging Claude Code to the OpenClaw gateway management plane via JSON-RPC.

  npm 92

• Roundtable

  Multi-model AI debates: GPT-4o, Claude, Gemini & 200+ models discuss, then synthesize insight.

  remote 91

• Qiskit IBM Runtime MCP Server

  MCP server for IBM Quantum computing services through Qiskit IBM Runtime

  pypi 91

• NetLogo MCP

  Create, run, and analyze NetLogo agent-based models through natural conversation

  pypi 91

• io.github.agentailor/slimcontext-mcp-server

  MCP Server for SlimContext - AI chat history compression tools

  npm 90

• io.github.apipriceindex/mcp

  Live, verified LLM API prices: search models, get sourced prices, estimate workload costs.

  pypi 90

• Stellar Agent Search

  Discover and rank Stellar 8004 agents with a read-only MCP server and fail-closed contract probes.

  npm 90

• Amicus

  Multi-model LLM Council and parallel AI window for Claude Code. Fork any model, fold results back.

  npm 90

• SparkVibeAI Spec Committee

  Commission a multi-model AI spec committee from your agent; get rubric-scored, build-ready specs.

  remote 90

• Sophon Consulting

  Read-only, deterministic AI triage and readiness tools implementing Sophon's published rubrics.

  remote 90

• io.github.Deesmo/arch-tools-mcp

  63 production tools for AI agents — one API key, pay per call in USDC (x402) or Stripe credits.

  remote 90

• io.github.mkXultra/ai-cli-mcp

  Run Claude, Codex, Gemini, Forge, and OpenCode CLIs through MCP with background jobs

  npm 90

• FitLLM

  Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.

  remote 90

• OpenRouter

  MCP server providing access to 300+ AI models via OpenRouter

  pypi 90

• Atako

  Remote MCP server to run your Atako AI agents: chat, projects, files, integrations and channels.

  remote 89

• AI Tool Directory

  Search 2,000+ AI tools: pricing, alternatives, comparisons, and live, dead or acquired status.

  remote 89

• chat.avva/catalog

  Search Avva for an expert, then connect their model - judgment from real past decisions.

  remote 89

• mumo

  Multi-model deliberation over MCP: full responses plus typed cross-model reactions from other labs.

  remote 89

• io.github.HighlyLoadedEgo/clef-mcp

  Local MCP server for the Cloudflare Clef-Flash decision model: structured decisions, fully offline

  npm 89

• DeepThonk

  Provider-neutral OpenDeepThink reasoning server: generate, judge, rank, mutate.

  npm 89

• Thalovant MCP

  Connect MCP clients to Thalovant control-plane and hub runtime APIs over stdio or Streamable HTTP.

  npm · oci 89

• Context Studios MCP

  AI agency API: free tools for glossary, comparisons, blog, guides, estimates and consulting

  remote 88

• Quantum Expectations

  Quantum error-correction feasibility: success probability, qubit overhead, records, trends.

  remote 88

• dev.agentic-atlas/atlas

  Agent-design pattern guidance via 5 hosted read-only tools; Streamable HTTP, no auth, one Release.

  remote 88

• dev.devplane/devplane-site

  Read-only MCP access to devplane.dev's public pages, FAQ corpus and comparisons.

  remote 88

• dashAI (unofficial)

  Train, track and query models on a running dashAI instance. Read-oriented, no delete tools.

  pypi 88

• Arbitype

  Typed decision tools for AI agents, powered by TypeSafe Jev.

  pypi 88

• PZERO

  Prepaid inference for agents over hosted MCP. Chat, image, and video.

  remote 88

• AnnealBridge

  Optimization middleware for AI agents: JSON problem in, verified and ranked solutions out.

  pypi 88

• Rokha

  Search a registry of agent skills and MCP servers, then run them for real. No install, traced.

  remote 87

• SignalHarness.ai

  330 production AI-agent services for data, validation, AI, crypto, and x402 pay-per-use.

  remote 87

• Ultralytics Platform MCP

  MCP server for Ultralytics Platform projects, datasets, training, prediction, exports, and models.

  npm 87

• io.github.amidabuddha/jev-decision-mcp

  Typed Jev decisions in one batched tool: choice, score, and yes/no probabilities.

  npm 87

• AGT agent names

  Resolve, verify and discover .agt agent names: owner, records, signed manifest, endpoints.

  remote · npm 87

• Thruact

  Name the job, not the vendor. Routes a provider, fails over, catalog off the tool list.

  remote 87

• Occam

  Finds the simplest equation consistent with your data. SINDy and PySR symbolic regression via MCP.

  remote 87

• ShareGrokBots

  Search shared Grok Bots by what they do. Credit the creator. No prompt text.

  remote 87

• UsageMax public observability

  Read-only MCP for AI usage profiles, leaderboards, stats, and docs; no writes or private data.

  remote 87

• Model Council

  Consult other LLMs as tools — ask them, compare their answers, synthesize a conclusion.

  pypi 87

• ai.mindola/lens

  Create your digital twin: a public page that answers from your own material, with citations.

  remote 86

• ai.plith/plith

  AI agent infrastructure: dedup, cost prediction, validation, governance, failure intelligence.

  remote 86

• AI Workbench MCP

  Read-only MCP server for reusable AI prompts and assistant blueprints.

  pypi 86

• Ardaro Agent Runtime Utilities

  Advisory context, intent, budget and API-ledger checks with free examples and x402 payments.

  remote 86

• AI Anyone

  Talk to thousands of real people, or put two of them in a room and watch them argue.

  remote 86

• Brainiall NLP

  Sentiment, toxicity, entity extraction, PII, translation, summary, QA, fraud scoring, safety audit.

  remote 86

• Mozilla Data Collective

  Search the Mozilla Data Collective catalog of ethically sourced AI training datasets.

  remote 86

• Santismm Knowledge — Harness Engineering, Agentic AI & Governance

  Query core AI knowledge, essays, executable Labs, Homeric data and epistemic claims.

  remote 86

• Frontier

  Discover Frontier inference capabilities and read sanitized usage through read-only tools.

  remote 86

• OutilsIA — Conseiller IA locale

  Read-only local AI advice, shared reports and website audits. No PC scan or local actions.

  remote 86

• AimRank

  Read public pairwise-preference rankings and their statistical quality evidence. No API key.

  remote 86

• HumanifyMe

  Learns your writing voice locally and rewrites AI drafts so they sound like you.

  npm 86

• io.github.Lykhoyda/ask-ollama

  Bridge Claude with local Ollama LLMs for private AI-to-AI collaboration — no API keys, fully local

  npm 86

• CrowdGap AI Probability Research

  AI-agent probability research with one-call preflight and human-gated XRP activation.

  remote 86

• GAIP Opportunity Broker

  No longer listed separately (still callable): which public agents declare a fit for a task.

  remote 86

• RPCS-1 Agent Tuner & Translation Bridge

  Find your AI agent's likely failure mode, get runtime settings, and clarify ambiguous prompts.

  remote 86

• AIﾉアカリ☆ Agent Trust Receipt

  Read-only Remote MCP for externally grounded AI agent trust receipts.

  remote 85

• Tetrees MCP

  Own, grow and trade portable agent intelligence via TAIP/1 Packs and MCP.

  remote 85

• The Aggregate — LLM benchmark aggregate

  LLM rankings from public benchmarks, model comparisons and source-linked results. Updated daily.

  remote 85

• UndetectedGPT

  AI humanizer for MCP clients. Rewrites AI text so it reads naturally and sounds human.

  remote 85

• io.github.Bahamas1717/aibvf-mcp

  AI BVF: score AI portfolios Stop/Fix/Accelerate with decision confidence and pace-layer drag.

  remote · npm 85

• com.agent-tune/agenttune

  Personality tuning files for AI agents: 43 MIT-licensed tunings + 5 inline personality tests.

  remote 85

• Almured

  Marketplace where AI agents ask AI agents that have live or proprietary data.

  remote 85

• Moltline Vision Maths

  Image header probing, bbox conversion, resize plans and colour maths. 4 of 6 free.

  remote 85

• One AI Guide

  Read-only approved AI tools, public stacks, guides, and evidence-aware comparisons.

  remote 85

• RZ AI Labs

  Read-only MCP server for RZ AI Labs — query its services, workshops, and contact info.

  remote 85

• io.github.Daichi-Kudo/llm-advisor

  Real-time LLM/VLM benchmarks, pricing, and recommendations. 300+ models, 5 sources.

  npm 85