io.github.salted-butter-joshua/dify-mcp

Official

by salted-butter-joshua · Python

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

This MCP server exposes Dify knowledge base retrieval capabilities to Cursor and other MCP-compatible clients. It connects to a self-hosted or remote Dify instance over HTTP and supports optional dataset allowlisting for access control.

🛠️ Key Features

Knowledge base discovery: list and inspect allowed datasets
Semantic retrieval: search chunks via POST /datasets/{dataset_id}/retrieve
Document browsing: list documents

🚀 Use Cases

Retrieve information from a Dify knowledge base within an MCP client (including Cursor)
Limit accessible retrieval to selected datasets via allowlisting

⚡ Developer Benefits

Uses MCP to integrate Dify retrieval with MCP-compatible tooling
Provides dataset-level selection through dataset_id-scoped retrieval

difyknowledge basecursor integrationknowledge retrievaldocumentationai context

README.md6 KBView on GitHub

dify-mcp

Expose Dify knowledge base retrieval capabilities via MCP (Model Context Protocol), for use in Cursor and other MCP-compatible clients.

Connect to a self-hosted or remote Dify instance over HTTP, with optional dataset allowlisting for access control.

Features

Knowledge base discovery — list and inspect allowed datasets
Semantic retrieval — search chunks via Dify POST /datasets/{dataset_id}/retrieve
Document browsing — list documents and segments within a dataset
Dataset allowlist — restrict access to specific dataset_id values
stdio transport — no manual server startup; the MCP client launches the process

Requirements

Python 3.11+
A running Dify instance with Knowledge Base API enabled
Network access from the machine running the MCP server to your Dify API endpoint
A Dify Knowledge Base API Key (Dify → Knowledge → Service API → API Key)

Quick Start

1. Clone and install

bash

git clone https://github.com/salted-butter-joshua/dify-mcp.git
cd dify-mcp

python3.11 -m venv .venv

# Windows
.venv\Scripts\python.exe -m pip install -e .

# macOS / Linux
.venv/bin/python -m pip install -e .

Verify import:

bash

# Windows
.venv\Scripts\python.exe -c "import dify_mcp; print('OK')"

# macOS / Linux
.venv/bin/python -c "import dify_mcp; print('OK')"

2. Configure environment

Copy the example env file and edit it:

bash

cp .env.example .env

env

DIFY_API_BASE=http://your-dify-host/v1
DIFY_API_KEY=dataset-your-api-key
DIFY_ALLOWED_DATASETS=dataset-uuid-1,dataset-uuid-2
DIFY_TIMEOUT=30
DIFY_VERIFY_SSL=false

Variable	Description
`DIFY_API_BASE`	Dify Knowledge API base URL, e.g. `http://192.168.1.100/v1`
`DIFY_API_KEY`	Knowledge Base API key
`DIFY_ALLOWED_DATASETS`	Comma-separated dataset UUIDs to expose (required)
`DIFY_TIMEOUT`	HTTP timeout in seconds (default: `30`)
`DIFY_VERIFY_SSL`	Verify TLS certificates (default: `false` for self-signed certs)

Run the health check:

bash

# Windows
.venv\Scripts\python.exe scripts/health_check.py

# macOS / Linux
.venv/bin/python scripts/health_check.py

3. Add to Cursor

You do not need to start the MCP server manually. Cursor launches it automatically via stdio.

Open Cursor Settings → MCP → Edit config
Add the following to mcpServers in your MCP config file:
- Windows: %USERPROFILE%\.cursor\mcp.json
- macOS / Linux: ~/.cursor/mcp.json
Replace paths and env values with your own
Restart Cursor

See mcp.json.example for a full example.

Windows example:

json

{
  "mcpServers": {
    "dify-knowledge": {
      "command": "/absolute/path/to/dify-mcp/.venv/Scripts/python.exe",
      "args": ["-m", "dify_mcp.server"],
      "cwd": "/absolute/path/to/dify-mcp",
      "env": {
        "DIFY_API_BASE": "http://your-dify-host/v1",
        "DIFY_API_KEY": "dataset-your-api-key",
        "DIFY_ALLOWED_DATASETS": "dataset-uuid-1,dataset-uuid-2",
        "DIFY_TIMEOUT": "30",
        "DIFY_VERIFY_SSL": "false"
      }
    }
  }
}

macOS / Linux example:

json

{
  "mcpServers": {
    "dify-knowledge": {
      "command": "/absolute/path/to/dify-mcp/.venv/bin/python",
      "args": ["-m", "dify_mcp.server"],
      "cwd": "/absolute/path/to/dify-mcp",
      "env": {
        "DIFY_API_BASE": "http://your-dify-host/v1",
        "DIFY_API_KEY": "dataset-your-api-key",
        "DIFY_ALLOWED_DATASETS": "dataset-uuid-1,dataset-uuid-2"
      }
    }
  }
}

4. Verify in Cursor

Cursor Settings → MCP → confirm dify-knowledge shows as enabled
In chat, try:
- List available Dify knowledge bases
- Search the knowledge base for "your query"

MCP Tools

Tool	Description
`list_datasets`	List knowledge bases within the allowlist
`get_dataset`	Get metadata for one dataset
`search_knowledge`	Retrieve relevant chunks (primary retrieval tool)
`list_documents`	List documents in a dataset
`list_document_segments`	List text segments for a document

Architecture

code

Cursor (MCP client)
    │ stdio
    ▼
dify-mcp (local process)
    │ HTTPS / HTTP
    ▼
Dify Knowledge API (/v1/datasets/...)

The MCP server runs locally on your machine and calls the Dify API over the network. Dify does not need to reach your machine.

Troubleshooting

Issue	Cause	Fix
`No matching distribution found for mcp`	Python < 3.11	Use Python 3.11+ in `.venv`
MCP shows error (red)	Wrong Python path, invalid key, or network issue	Check `mcp.json` paths and env vars
`401 Unauthorized`	Invalid API key	Regenerate key in Dify Service API panel
`Dataset not in allowed list`	UUID not in `DIFY_ALLOWED_DATASETS`	Add the dataset UUID to the allowlist
Health check missing env vars	`.env` not found	Ensure `.env` exists in the project root
Connection timeout	Dify unreachable	Check network / VPN / firewall

Project Structure

code

dify-mcp/
├── src/dify_mcp/
│   ├── server.py        # MCP entry point
│   ├── config.py        # Settings and allowlist
│   ├── dify_client.py   # Dify Knowledge API client
│   └── formatters.py    # Response formatting
├── scripts/
│   └── health_check.py  # Connectivity test
├── mcp.json.example     # Cursor MCP config template
├── .env.example         # Environment variable template
└── Dify-API.md          # Local API path reference

API Reference

Security Notes

Never commit .env or API keys to version control
A single Knowledge Base API key can access all visible datasets under the account — use DIFY_ALLOWED_DATASETS to limit exposure
Prefer running MCP locally; keep API keys in mcp.json env or .env on your machine only

Install

Configuration

Environment variables

DIFY_API_BASErequired

Dify Knowledge API base URL, e.g. http://192.168.1.100/v1

DIFY_API_KEYrequiredsecret

Dify Knowledge Base API key

DIFY_ALLOWED_DATASETSrequired

Comma-separated dataset UUIDs to expose

DIFY_TIMEOUT

HTTP timeout in seconds (default: 30)

DIFY_VERIFY_SSL

Verify TLS certificates (default: false)

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "dify-mcp": {
      "command": "uvx",
      "args": [
        "dify-mcp"
      ],
      "env": {
        "DIFY_API_BASE": "<YOUR_DIFY_API_BASE>",
        "DIFY_API_KEY": "<YOUR_DIFY_API_KEY>",
        "DIFY_ALLOWED_DATASETS": "<YOUR_DIFY_ALLOWED_DATASETS>",
        "DIFY_TIMEOUT": "<YOUR_DIFY_TIMEOUT>",
        "DIFY_VERIFY_SSL": "<YOUR_DIFY_VERIFY_SSL>"
      }
    }
  }
}

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

dify-mcp

Features

Requirements

Quick Start

1. Clone and install

2. Configure environment

3. Add to Cursor

4. Verify in Cursor

MCP Tools

Architecture

Troubleshooting

Project Structure

API Reference

Security Notes

Install

Configuration

Related servers