AI & ML
Model inference, embeddings, vision, and AI pipelines.
No benchmark data published for this category yet — all entries below are registry listings.
| Server | Status | Stars | Namespace | Transports | Description |
|---|---|---|---|---|---|
| basic-memory | Listed | 3,463 | GitHub | stdio | Local-first knowledge management with bi-directional LLM sync via Markdown files. |
| beever-atlas | Listed | 416 | GitHub | stdio | Open-source LLM knowledge base: team chat into a typed knowledge graph and auto-generated wiki. |
| browserbasehq-mcp-browserbase | Listed | 3,408 | Domain-verified | remote | Provides cloud browser automation capabilities using Stagehand and Browserbase, enabling LLMs to i… |
| mcp-omnisearch | Listed | 334 | GitHub | stdio | MCP server for integrating Omnisearch with LLMs |
| mcp-youtube-transcript | Listed | 458 | GitHub | stdio | An MCP server retrieving transcripts of YouTube videos |
| Microsoft Learn MCP | Listed | 1,785 | Domain-verified | remote | Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs. |
| mockserver | Listed | 4,920 | Domain-verified | stdio | Mock, record/replay, verify and chaos-test any HTTP, REST, gRPC or LLM dependency over MCP. |
| nanobanana-mcp-server | Listed | 380 | GitHub | stdio | An MCP server that provides image generation and editing capabilities |
| Perceptdot GitHub | Listed | — | GitHub | stdio | AI agent vision for GitHub repository monitoring — with ROI measurement. |
| Perceptdot Sentry | Listed | — | GitHub | stdio | AI agent vision for Sentry error tracking — with ROI measurement. perceptdot.com |
| screenpipe | Listed | 20,328 | GitHub | stdio | Search your local screen recordings, audio transcripts, and computer activity from screenpipe. |
| docfork-mcp (smithery) | Listed | 489 | Domain-verified | remote | @latest documentation and code examples to 9000+ libraries for LLMs and AI code editors in a singl… |
| StackQL MCP Server | Listed | 861 | GitHub | stdio | SQL-native query and provisioning engine for cloud infrastructure, served over MCP. |
| aaa-mcp | Listed | 49 | GitHub | stdio | Constitutional AI Governance with 13 enforced floors (F1-F13) and tri-witness consensus for LLMs. |
| acquis | Listed | 0 | Domain-verified | remote | Verified EU law: verbatim, signed provisions with EUR-Lex links. Read-only, not legal advice. |
| activitypub-mcp | Listed | 17 | GitHub | stdio | Read-only-by-default MCP server: let LLMs explore the Fediverse — Mastodon, Misskey, Pleroma. |
| aeo-mcp | Listed | 0 | GitHub | stdio | AEO tools for AI agents: crawler permissions, llms.txt, structured data, AI-readiness audit. |
| aether-developer | Listed | 0 | GitHub | stdio | Hybrid search over SEC filings, earnings transcripts, and a third-party data marketplace. |
| aether studio — AI Image Generation, Editing & Creative Workflow | Listed | — | GitHub | remote | Generate, edit, and explore AI images. Flux, Imagen, LoRA identity swap, upscale, and more. |
| mcp-server | Listed | 0 | GitHub | stdio | Real-time physical perception for AI agents — vision, spatial, acoustic, environmental |
| agence | Listed | 4 | GitHub | stdio | AI governance MCP server — policy enforcement, skills, memory, multi-LLM consensus |
| Agent Comms | Listed | 12 | GitHub | stdio | Cross-harness communication mesh for LLM agents — rooms, DMs, presence, and visibility over TCP |
| agent-cost-allocator-mcp | Listed | 0 | GitHub | stdio, remote | Agent Cost Allocator MCP — multi-tenant LLM cost attribution for chargeback billing. Companion to |
| agent-godmode | Listed | 0 | GitHub | stdio | Sandboxed workspace MCP: file ops, argv-only run_command, list_files; BYO LLM prompts. |
| agent-media-toolkit | Listed | 0 | GitHub | remote | 15 media & data tools for AI agents: search, transcribe, subtitles, voiceover, translate & more. |
| agent-output-guard | Listed | 0 | GitHub | stdio | Validate and verify data from other agents before acting on it. Zero LLM costs. |
| agent-pay | Listed | — | GitHub | stdio | Payment gateway for AI agents with tool discovery, provisioning, metering, and reliability tools. |
| Agent Readiness Auditor | Listed | 0 | GitHub | stdio | Audits any website for AI agent readiness and safety, scoring prompt injection risk and llms.txt. |
| agent-ready-kit | Listed | 0 | Domain-verified | remote | Agent-readiness scanner (0-5 score), robots.txt + llms.txt generators, managed agent enablement. |
| Agent Ready | Listed | 1 | GitHub | stdio, remote | Scan any URL for AI agent readability — Vercel Spec, llmstxt.org, and agent-protocol manifests. |
| Agent Utility API | Listed | — | GitHub | remote | x402 pay-per-call tools: company enrichment, PDF extraction, Amazon/KDP data, YouTube transcripts. |
| agent-web — URL to LLM-ready markdown: a polite, robots-respecting web page reader (free) | Listed | 0 | GitHub | remote | URL to clean markdown for LLMs: a polite, robots.txt-respecting web reader. Free, no API key |
| mcp-server | Listed | — | Domain-verified | stdio | On-brand image generation (product shots, app icons, OG cards, sprites) for AI coding agents. |
| agentcast | Listed | 1 | GitHub | stdio | Structured-output enforcer: extract and validate JSON from messy LLM text. |
| Agentic Observability MCP | Listed | 0 | GitHub | stdio | Agent tracing, cost tracking, anomaly detection for LLM agents |
| agentmetal | Listed | 2 | Domain-verified | stdio | Rent a Linux VPS from an AI agent: provision, SSH in, run commands. Pay USDC (x402) or card. |
| agentshield-mcp | Listed | 0 | GitHub | stdio | Detect prompt injection, jailbreak, and social-engineering attacks in LLM agents. |
| AgentSUMO | Listed | 5 | GitHub | stdio | MCP server for LLM-driven SUMO traffic simulation, scenario design, and result analysis. |
| Agentverse Memory | Listed | — | GitHub | remote | Graph-native persistent memory for AI agents — 33 MCP tools, zero-LLM writes. |
| agentvet | Listed | 1 | GitHub | stdio | Validate tool-call args before execution. Returns LLM-friendly retry hints. |
| agrobr | Listed | 26 | GitHub | stdio | Brazilian agricultural data for LLMs — prices, crops, climate, deforestation. |
| AI Agent Search Optimization | Listed | — | GitHub | stdio | Audit AI search readiness, generate llms.txt drafts, and build GEO/AEO prompt matrices for websites. |
| AI API Radar | Listed | — | Domain-verified | remote | Live LLM API price + status radar across 11 providers, with public per-model price HISTORY. |
| ActableSite AI Crawler Monitor | Listed | 0 | Domain-verified | remote | Check AI crawler robots.txt policy and monitor public-site policy, sitemap, and llms.txt changes. |
| AI Firewall MCP | Listed | 0 | GitHub | stdio | Multi-agent LLM security layer detecting prompt injection and jailbreaks. |
| AI Guardian | Listed | 0 | GitHub | stdio | Governed local-LLM (Ollama) observability: model policy, prompt scanner, 18 tools. |
| ai·rete·rag | Listed | — | Domain-verified | stdio | Auditable rule-based decisions with RAG explanations: a Rete engine decides, an LLM explains why. |
| AI Scanner | Listed | 1 | GitHub | stdio | Scan codebases for LLM/AI SDK usage, exposed API tokens, and hardcoded secrets. |
| ai-seo | Listed | 2 | GitHub | stdio | MCP server for AI-SEO auditing: schema, robots.txt, llms.txt, citation scoring, and AEO/GEO rewrites |
| AI Site Scorer | Listed | — | GitHub | remote | Check website AI-readiness: Schema.org, llms.txt, E-E-A-T, robots.txt. Works in Cursor & Claude. |
| Aigist | Listed | 0 | Domain-verified | remote | Publish & manage shareable HTML/Markdown pages from your LLM, with access control. |
| aiglare | Listed | 1 | GitHub | stdio | Audit AI/LLM features for governance guardrails: confidence, fallback, validation, human-in-loop. |
| Aiven MCP | Listed | 26 | Domain-verified | stdio, remote | Provision PostgreSQL, manage Apache Kafka, and deploy apps with Aiven - all from your AI assistant. |
| Alchemy | Listed | 0 | GitHub | stdio | Serves the Alchemy writing ruleset to any agent, so its prose loses the usual LLM tells. |
| alex-llm-attack-mcp-server | Listed | 3 | Domain-verified | remote | Query and retrieve information about various adversarial tactics and techniques used in cyber atta… |
| Alibaba Cloud DashScope — Qwen | Listed | 84 | GitHub | stdio | Alibaba Cloud DashScope MCP: Qwen chat, embeddings, and model discovery on your own account. |
| Amicus | Listed | 0 | GitHub | stdio | Multi-model LLM Council and parallel AI window for Claude Code. Fork any model, fold results back. |
| anchor-x402 | Listed | 1 | GitHub | stdio | 14-tool x402 MCP: 9 onchain primitives + 5 LLM endpoints. USDC pay-per-call on Base or Solana. |
| animica | Listed | 4 | GitHub | stdio, remote | OpenAI-compatible AI inference, code, embeddings & agent tools for bots — and mine ANM. |
| anybrowse | Listed | 4 | GitHub | remote | Converts any URL to clean, LLM-ready Markdown using real Chrome browsers |
| Sugra API | Listed | 1 | Domain-verified | stdio, remote | Gateway between LLM agents and world data through eight tools and a bundled endpoint catalog. |
| API Locker | Listed | 0 | GitHub | stdio | Encrypted credential vault: LLM, service & OAuth keys. 21-tool MCP server for your AI agent. |
| apollo-salesforce-mapper | Listed | — | Domain-verified | remote | Apollo->Salesforce Lead mapper. No LLM. Strict-fail required fields. PASS/REPAIR/FAIL verdict. |
| apple-voice-memo-mcp | Listed | 6 | GitHub | stdio | Access Apple Voice Memos on macOS. List, get audio, extract and generate transcripts. |
| server | Listed | — | Domain-verified | stdio | Observability MCP server: query LLM cost/errors/latency & operate alerts/evals from Claude/Cursor |
| mcp-server | Listed | 1 | GitHub | stdio | Detect fabrication and hallucination in any LLM output. 30+ models supported. |
| artscii | Listed | 1 | GitHub | stdio | LLMs can't draw. This MCP can. 81 arts + 100 kaomoji + diagrams + charts. |
| Ascend GTM Gateway | Listed | — | Domain-verified | remote | 34-tool GTM gateway: CRMs, ad platforms, analytics, Google Workspace, AWS, and LLM orchestration. |
| ask-llm | Listed | 12 | GitHub | stdio | Unified MCP server — auto-detects Gemini, Codex, Claude, Ollama, and Antigravity providers |
| ask-ollama | Listed | 12 | GitHub | stdio | Bridge Claude with local Ollama LLMs for private AI-to-AI collaboration — no API keys, fully local |
| ATOM Pricing Intelligence | Listed | 0 | GitHub | stdio, remote | The Global Price Benchmark for AI Inference. 1,600+ SKUs, 40+ vendors, 14 price indexes. |
| audio-analyzer | Listed | 47 | GitHub | stdio | Gives LLMs ears. Spectral, harmonic, rhythm, stereo, and structural audio analysis. |
| Audioscrape Audio Intelligence | Listed | — | Domain-verified | remote | The audio intelligence layer. Search podcast transcripts, speakers, and entities across 250K+ shows. |
| three.ws Audio | Listed | 84 | GitHub | stdio | Text-to-speech, speech-to-text, audio-to-face lipsync, and motion-capture clips for 3D agents. |
| authenticated-llm-agent | Listed | 1 | GitHub | remote | JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. |
| authenticated-mcp-agent | Listed | 1 | GitHub | remote | JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. |
| authenticated-multi-llm-agent | Listed | 1 | GitHub | remote | Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion f |
| auto-skill-loader | Listed | 0 | GitHub | stdio | Auto-loads skills into agent sessions. MiniMax vision and search proxy. |
| Auxen | Listed | 0 | Domain-verified | remote | Provision private AI model endpoints on dedicated GPUs (Llama, Qwen, Mistral). Pay per minute. |
| AWT (AI Watch Tester) | Listed | 1 | GitHub | stdio | AI-powered E2E testing MCP server. Detects and auto-fixes UI bugs via DevQA Loop and Vision AI. |
| memex | Listed | 1 | GitHub | stdio | Persistent memory for AI agents — semantic + recency search, ONNX embeddings, Docker Compose. |
| Bardo | Listed | — | Domain-verified | remote | Identity & continuity for AI agents, gated by a proof-of-being-an-LLM puzzle. |
| bash-vet-mcp | Listed | 0 | GitHub | stdio | Vet LLM-emitted shell commands BEFORE execution. 26 destructive-pattern rules / 8 families. |
| Bee — The Progressive Intelligence Engine | Listed | 0 | GitHub | stdio | Bee — The Progressive Intelligence Engine: tiered LLM, 4 tools, hosted API, free tier. |
| LiteLLM Multi-Model API | Listed | — | GitHub | stdio | Access 100+ LLMs with one API: GPT-4, Claude, Gemini, Mistral, and more. |
| bies-guardian | Listed | — | GitHub | remote | Deterministic sealed verdicts on public claims and startup ideas (0-LLM claim-safety guardian). |
| biolit | Listed | 2 | GitHub | stdio | LLM-assisted biomedical literature screening and extraction for PubMed, GEO, and preprints. |
| blinkpdf | Listed | — | Domain-verified | remote | Render Markdown and LLM output into accessible PDF/UA-1 PDFs. No headless Chromium. |
| Blueprint Chart | Listed | 0 | GitHub | stdio | The open chart format an LLM writes and the browser renders — to interactive, accessible SVG. |
| botverse | Listed | 1 | GitHub | stdio | Transcode video, convert docs & transcribe audio for AI agents. Free $1 trial, no card. |
| Text to Speech API | Listed | 0 | GitHub | remote | Convert text to MP3 speech audio in 50+ languages. x402 micropayment. |
| three.ws Brain | Listed | 84 | GitHub | stdio | List LLM providers and run chat completions through the three.ws multi-provider router. |
| brandonbosco-sigao-scf-mcp | Listed | — | Domain-verified | remote | Provides access to Civic Plus - See Click Fix, allowing you to interact with your data via an LLM.… |
| Browsegrab | Listed | 0 | GitHub | stdio | Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab. |
| cache-proxy | Listed | — | GitHub | remote | LLM caching proxy (x402 USDC on Base) - exact + semantic cache. Free health. |
| calcfi-mcp | Listed | — | GitHub | stdio | 24 free personal-finance + macro tools (mortgage, paycheck, tax, FRED, BLS) for LLM agents. |
| callmybot-cookbook-mcp-server | Listed | 0 | Domain-verified | remote | Count occurrences of any character in your text instantly. Specify the character and get precise c… |
| callmybot-domoticz | Listed | 0 | Domain-verified | remote | Greet anyone by name with a friendly hello. Explore the origin of 'Hello, World' for context in de… |
| callmybot-hello-mcp-server | Listed | 0 | Domain-verified | remote | Generate quick, friendly greetings by name. Personalize salutations for any context. Explore the o… |
| CAPI Gateway | Listed | 9 | GitHub | stdio | Apache Camel API Gateway with REST-to-MCP bridging for LLM agents. |
Showing 100 of 678 servers in this category.