Best AI & ML MCP Servers for VS Code

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

Setting up MCP servers in VS Code

VS Code's MCP support is native (via GitHub Copilot's agent mode), configured in .vscode/mcp.json per workspace or through the "MCP: Open User Configuration" command for a config that applies everywhere. One thing that trips people up moving a config from Claude Desktop or Cursor: VS Code's top-level key is "servers", not "mcpServers" — the two aren't interchangeable.

Because .vscode/mcp.json is a normal workspace file, it can be committed alongside project code the same way project-scoped Cursor configs can — a team opening the repo in VS Code gets the same MCP servers without extra setup.

#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

Streamline agent paths using a 11-dependency oversight utility.

53502TypeScript
4

Manage your account balance and check model availability through standard MCP tools.

53351TypeScript
5

Leverage TypeScript-based prompt management by connecting your IDE to Langfuse for structured retrieval of production assets.

49173TypeScript
6

Perform web and image searches with integrated query expansion capabilities.

48848TypeScript
7

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

4690,284TypeScript
8

Use TypeScript-based MCP tools to offload generative visual tasks to the Replicate API.

45107TypeScript
9

Use project-specific directory structures to keep documentation organized and accessible.

41919TypeScript
10

Leverage TypeScript-based tool definitions to poll for request status and handle pending agent tasks.

352TypeScript
11

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

33983TypeScript
12

Implements hybrid search for technical documentation by combining keyword matching with embedding models.

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 + VS Code: frequently asked questions

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

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 VS Code config.

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

Add an entry under "servers" in .vscode/mcp.json in your workspace, or run "MCP: Open User Configuration" from the command palette for a global config. 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 VS Code?

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 VS Code.

›How many AI & ML MCP servers work with VS Code?

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

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

It's simply VS Code's own schema — Claude Desktop, Cursor, and Windsurf all use "mcpServers", but a config copied between them and VS Code needs that one key renamed. An AI & ML server goes in the exact same place as any other VS Code MCP server — there's no category-specific config location.

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

Yes — run "MCP: Open User Configuration" from the command palette to edit a config that applies across all your workspaces. That's true whether you're adding Sequential Thinking MCP Server or any other AI & ML server.