The best AI & ML MCP servers
Give your agents the AI and machine-learning building blocks they need — vector databases, embeddings, reasoning tools, and model gateways — as callable MCP tools. Connect once on BusinessMCP and every agent, on any model, works from the same unified endpoint.
How we rank
Entries are ordered by install count with official, hand-verified connectors first. The directory refreshes as new servers ship; every entry links to a detail page with real capabilities, example prompts, and setup instructions.
| Server | By | Price | Installs |
|---|---|---|---|
| Math-MCP | EthanHenrickson | Free | 752.4k |
| Memory | anthropic | Free | 180k |
| Sequential Thinking | anthropic | Free | 90k |
| OpenAI | openai | Free | 55k |
| GitHub Copilot MCP | github | Free | 50k |
| Mesh MCP | clay-inc | Free | 45.4k |
| Pinecone | pinecone | Free | 35k |
| LangChain MCP Adapters | langchain | Free | 35k |
| Chroma | chroma | Free | 25k |
| Replicate | replicate | Free | 25k |
Math-MCP
EthanHenrickson
Enable LLMs to perform accurate numerical calculations with a simple API. Leverage basic arithmetic and statistical functions.
Memory
anthropic
Knowledge graph-based persistent memory system for AI. Store and retrieve structured information across conversations.
Sequential Thinking
anthropic
Dynamic problem-solving through sequential thought processes. Break complex problems into manageable steps.
OpenAI
openai
Access OpenAI APIs through MCP. Use GPT models, DALL-E, Whisper, and embeddings in agent workflows.
GitHub Copilot MCP
github
GitHub Copilot integration via MCP. Code completions, explanations, and chat in any MCP client.
Mesh MCP
clay-inc
Access your network seamlessly with a simple and efficient server. Leverage a variety of tools to enhance your applications and workflows.
Pinecone
pinecone
Vector database for semantic search and RAG. Store, query, and manage vector embeddings at scale.
LangChain MCP Adapters
langchain
Bridge between LangChain agents and MCP servers. Use any MCP server as a LangChain tool.
Chroma
chroma
Open-source vector database for AI applications. Store and retrieve embeddings for RAG and semantic search.
Replicate
replicate
Run ML models in the cloud. Access thousands of open-source models for image generation, LLMs, and more.
DeepSeek
deepseek-ai
Access DeepSeek AI models through MCP. Code generation, reasoning, and general AI assistance.
MindsDB
mindsdb
AI query engine for federated data sources. Run ML predictions through SQL on any database.
Weaviate
weaviate
Vector search engine with hybrid search capabilities. Combine vector and keyword search for optimal results.
Hyperbolic
hyperbolic-labs
Access GPU compute for AI inference. Run open-source models on demand with pay-per-use pricing.
Bitrix24 MCP-DEV
ExaltedTrou6
MCP server for Bitrix24 provides AI assistants with structured access to the Bitrix24 API for integration development.
Context Awesome
bh-rat
Provide AI agents with instant access to curated resources from over 8,500 awesome lists and more than 1 million items.
Tailwind Svelte Assistant
CaullenOmdahl
Instant access to SvelteKit and Tailwind CSS documentation along with ready-to-use Svelte component snippets.
Frequently asked questions
What is an AI & ML MCP server?
It exposes AI/ML capabilities — vector search, embeddings, RAG, or model APIs — as agent-callable functions over the Model Context Protocol, so any AI agent can use them without custom integration code.
Can I combine several AI tools in one workflow?
Yes. BusinessMCP unifies every connected server behind one hosted MCP endpoint, so an agent can chain a vector search, an embedding call, and a model query in a single thread.
Do these work across Claude, GPT, and Gemini?
Yes — every server on the registry is model-agnostic. Connect once and the same tools work across all major models and local agents.
Browse other categories
Connect a ai & ml tool in one click
Free forever plan, no credit card. Your first two tools are on us — set up in five minutes.
Get started free