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).

#ServerSecurity scoreStarsLanguage
1

Dynamic and reflective problem-solving through a structured step-by-step thinking process.

7690,284TypeScript
2

Persistent shared memory backend for AI agents using knowledge graphs and REST APIs.

651,940Python
3

Access MiniMax AI models directly through the Model Context Protocol.

581,577Python
4

Hugging Face Hub and Gradio app access for your AI assistant workflows.

58294TypeScript
5

Centralize and structure internal documentation into a managed AI knowledge hub.

541,405Python
6

Monitor agent activity with research-backed Chain-Pattern Interrupt oversight.

53502TypeScript
7

DeepSeek V4 API access including chat, completion, and account balance tools.

53351TypeScript
8

Local LLMs interact with MCP servers through this Python-based client interface.

50821Python
9

Provider Abstraction Layer orchestrating multiple AI models and CLIs in one workflow.

4911,746Python
10

Access and manage your Langfuse prompt library directly from your AI agent interface.

49173TypeScript
11

Web content extraction, academic research search, and image retrieval tools.

48848TypeScript
12

Persistent knowledge graph memory allowing AI to retain user information across sessions.

4690,284TypeScript
13

Flux-based image and SVG generation capabilities via Replicate API endpoints.

45107TypeScript
14

Multi-agent sequential thinking processes for deep analysis and problem decomposition.

42305Python
15

Remote memory bank management for multi-project file structure and validation.

41919TypeScript
16

Vector database collections and search tools now available directly in Weaviate.

39161—
17

Resemble AI documentation access for AI assistants via topic lookup and search.

381Python
18

ElevenLabs text-to-speech and audio processing for your AI assistant.

361,536Python
19

Human-in-the-loop approval requests for sensitive agent actions using confirm.dev.

352TypeScript
20

Local Ollama models execute tools through diverse MCP-compatible server plugins.

33983TypeScript
21

LightRAG API integration for document retrieval, graph management, and status monitoring.

31122Python
22

Repository indexing and structural code analysis for AI agents at high speeds.

2843,086C
23

Persistent long-term memory integration for AI agents via semantic search.

28684Python
24

Track structured reasoning sessions with audit trails and revision-aware state logging.

23950Python
25

Roo Code memory-bank files management via structured MCP tool interactions.

2357JavaScript
26

Google Gemini API access for web search and model-driven task delegation.

2354Python
27

Private document search using local indexing and hybrid retrieval methods.

20393TypeScript
28

LogSeq knowledge base access for Claude to read, create, and manage your notes.

20327Python
29

Milvus vector database functionality integration for your AI workflows.

20243Python
30

Local LLM access via the Ollama SDK for MCP-compatible AI applications.

15171TypeScript
31

Ollama local LLM management and chat completion via the Model Context Protocol.

1574JavaScript
32

Persistent memory for LLMs using the Mem0 API for cross-session data recall.

1398TypeScript
33

Pinecone index records accessed through semantic search and document tools.

0149Python