Best AI & ML MCP Servers for Windsurf

Top 15 of 15 AI & ML MCP servers that work with Windsurf, ranked by security score — every entry below is human-reviewed, not just scraped. Every row has a one-click config for Windsurf — no need to open each page.

Setting up MCP servers in Windsurf

Windsurf (by Codeium) surfaces MCP servers through Cascade, its agentic chat panel — once a server is configured, Cascade can call its tools directly during a conversation without any extra steps on your part.

Like Claude Desktop and Cursor, Windsurf uses a single mcpServers object in its config file, so a config written for one of those two clients needs no key renaming to work in Windsurf — only the file path changes.

#ServerSecurity scoreStarsLanguageConfig
1

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

7690,284TypeScript
2

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

58294TypeScript
3

Deploy research-backed monitoring for improved task reliability.

53502TypeScript
4

Stream structured responses with configurable reasoning effort for complex tasks.

53351TypeScript
5

Use this server to fetch and compile Langfuse prompts, ensuring your AI assistant operates with up-to-date, versioned prompt configurations.

49173TypeScript
6

Use parallel read and search tools for rapid research and data gathering.

48848TypeScript
7

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

4690,284TypeScript
8

Configure environment variables to switch between specialized image models for creative tasks.

45107TypeScript
9

Implement type-safe operations for reading and updating local memory bank files.

41919TypeScript
10

Use this server to log and audit agent decision-making processes through an external immutable record.

352TypeScript
11

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

33983TypeScript
12

Maintains data privacy by processing all document parsing and storage locally via the MCP protocol.

20393TypeScript
13

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

15171TypeScript
14

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

1574JavaScript
15

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

1398TypeScript

AI & ML + Windsurf: frequently asked questions

›What's the best AI & ML MCP server for Windsurf?

Sequential Thinking MCP Server currently ranks highest among AI & ML MCP servers, with a security score of 76/100, officially maintained by the vendor. Hf MCP Server (58/100) is the next best option. Every server below has a one-click Windsurf config.

›How do I add an AI & ML MCP server to Windsurf?

Add an entry under "mcpServers" in ~/.codeium/windsurf/mcp_config.json, then reload Windsurf. The same steps apply to Sequential Thinking MCP Server, the top-ranked AI & ML server below.

›Are AI & ML MCP servers safe to use with Windsurf?

3 of the 15 AI & ML MCP servers below are officially maintained by its vendor; the rest are independently reviewed. Every score comes from real signals — permissions requested, authentication, maintenance activity — not a marketing claim. All of them are compatible with Windsurf.

›How many AI & ML MCP servers work with Windsurf?

15 AI & ML MCP servers have a ready-to-use Windsurf config right now, ranked by security score below.

›Where do I put the AI & ML MCP server config for Windsurf?

~/.codeium/windsurf/mcp_config.json. An AI & ML server goes in the exact same place as any other Windsurf MCP server — there's no category-specific config location.

›Do I need to restart Windsurf after adding an AI & ML MCP server?

Cascade is Windsurf's agentic chat panel — it's what actually calls your configured MCP servers' tools during a conversation. That's true whether you're adding Sequential Thinking MCP Server or any other AI & ML server.