Dify MCP Server: Install & Setup

Install Dify in Claude Code

Claude Code

claude mcp add dify -e DIFY_API_BASE=... -e DIFY_API_KEY=... -e DIFY_ALLOWED_DATASETS=... -- uvx dify-mcp

mcp.json (Claude Desktop, Cursor, VS Code, Windsurf)

{
  "mcpServers": {
    "dify": {
      "command": "uvx",
      "args": [
        "dify-mcp"
      ],
      "env": {
        "DIFY_API_BASE": "...",
        "DIFY_API_KEY": "...",
        "DIFY_ALLOWED_DATASETS": "..."
      }
    }
  }
}

Replace each ... with your own value.

Frequently asked questions

What does the Dify MCP server do?

MCP server exposing Dify knowledge base retrieval to Cursor and other MCP clients

Is the Dify MCP server free?

The server is free, but you will likely need an account. The server itself is free, but it connects to a service that needs an account or API key, which may have paid tiers. Check the provider for current pricing.

Does Dify run locally or remotely?

Local. Runs on your machine (stdio). You install it with npx, uvx, Docker or from source.

How do I add Dify to Claude Code?

Run: claude mcp add dify -e DIFY_API_BASE=... -e DIFY_API_KEY=... -e DIFY_ALLOWED_DATASETS=... -- uvx dify-mcp

More knowledge, memory & rag MCP servers

View all

Dubstrata

MuzikayiseKhuzwayo/dubstrata

Dubstrata: Causal Financial & Narrative CDN providing Graph RAG & Deep Research Reports

LocalAccount needed

DevSpeak

io.github.juanjaragavi/devspeak

Improve or correct developer writing, or turn rough notes into technical specs, from your agent.

Local + RemoteAccount needed

dVeracity Semantic API

d-veracity/semantic-mcp

Natural-language queries over a verified emissions knowledge graph, plus standards validation

Local + RemoteAccount needed

Deerdawn

HissingSpider/deerdawn-mcp

AI session memory: the brief your AI reads before every session so no session starts cold.

Local + RemoteFree

EleSync

darknodebros/EleSync

Private local-first AI workspace for shared context, knowledge, tasks, and memories

LocalFree

darwin-memo

rogermsc/darwin-memo

Self-curating agent memory kept honest by survival-based selection over measured outcomes.

LocalFree