AI & ML MCP Servers
Model inference, embeddings, and ML pipelines.
33 servers in this category, ranked by security score below. 4 are officially maintained by the vendor. Current top pick: Sequential Thinking MCP Server (76/100).
| # | Server | Security score | Stars | Language |
|---|---|---|---|---|
| 1 | Sequential Thinking MCP ServerOfficial Dynamic and reflective problem-solving through a structured step-by-step thinking process. | 76 | 90,284 | TypeScript |
| 2 | Persistent shared memory backend for AI agents using knowledge graphs and REST APIs. | 65 | 1,940 | Python |
| 3 | Access MiniMax AI models directly through the Model Context Protocol. | 58 | 1,577 | Python |
| 4 | Hugging Face Hub and Gradio app access for your AI assistant workflows. | 58 | 294 | TypeScript |
| 5 | Centralize and structure internal documentation into a managed AI knowledge hub. | 54 | 1,405 | Python |
| 6 | Monitor agent activity with research-backed Chain-Pattern Interrupt oversight. | 53 | 502 | TypeScript |
| 7 | DeepSeek V4 API access including chat, completion, and account balance tools. | 53 | 351 | TypeScript |
| 8 | Local LLMs interact with MCP servers through this Python-based client interface. | 50 | 821 | Python |
| 9 | Provider Abstraction Layer orchestrating multiple AI models and CLIs in one workflow. | 49 | 11,746 | Python |
| 10 | Langfuse MCP ServerOfficial Access and manage your Langfuse prompt library directly from your AI agent interface. | 49 | 173 | TypeScript |
| 11 | Web content extraction, academic research search, and image retrieval tools. | 48 | 848 | TypeScript |
| 12 | Memory MCP ServerOfficial Persistent knowledge graph memory allowing AI to retain user information across sessions. | 46 | 90,284 | TypeScript |
| 13 | Flux-based image and SVG generation capabilities via Replicate API endpoints. | 45 | 107 | TypeScript |
| 14 | Multi-agent sequential thinking processes for deep analysis and problem decomposition. | 42 | 305 | Python |
| 15 | Remote memory bank management for multi-project file structure and validation. | 41 | 919 | TypeScript |
| 16 | Vector database collections and search tools now available directly in Weaviate. | 39 | 161 | — |
| 17 | Resemble AI documentation access for AI assistants via topic lookup and search. | 38 | 1 | Python |
| 18 | ElevenLabs MCP ServerOfficial ElevenLabs text-to-speech and audio processing for your AI assistant. | 36 | 1,536 | Python |
| 19 | Human-in-the-loop approval requests for sensitive agent actions using confirm.dev. | 35 | 2 | TypeScript |
| 20 | Local Ollama models execute tools through diverse MCP-compatible server plugins. | 33 | 983 | TypeScript |
| 21 | LightRAG API integration for document retrieval, graph management, and status monitoring. | 31 | 122 | Python |
| 22 | Repository indexing and structural code analysis for AI agents at high speeds. | 28 | 43,086 | C |
| 23 | Persistent long-term memory integration for AI agents via semantic search. | 28 | 684 | Python |
| 24 | Track structured reasoning sessions with audit trails and revision-aware state logging. | 23 | 950 | Python |
| 25 | Roo Code memory-bank files management via structured MCP tool interactions. | 23 | 57 | JavaScript |
| 26 | Google Gemini API access for web search and model-driven task delegation. | 23 | 54 | Python |
| 27 | Private document search using local indexing and hybrid retrieval methods. | 20 | 393 | TypeScript |
| 28 | LogSeq knowledge base access for Claude to read, create, and manage your notes. | 20 | 327 | Python |
| 29 | Milvus vector database functionality integration for your AI workflows. | 20 | 243 | Python |
| 30 | Local LLM access via the Ollama SDK for MCP-compatible AI applications. | 15 | 171 | TypeScript |
| 31 | Ollama local LLM management and chat completion via the Model Context Protocol. | 15 | 74 | JavaScript |
| 32 | Persistent memory for LLMs using the Mem0 API for cross-session data recall. | 13 | 98 | TypeScript |
| 33 | Pinecone index records accessed through semantic search and document tools. | 0 | 149 | Python |