Dify Agent Mcp Sse
@junjiem
About Dify Agent Mcp Sse
Dify 1.0 Plugin Support MCP Tools Agent strategies
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"server_name1": {
"transport": "sse",
"url": "http://127.0.0.1:8000/sse",
"headers": {},
"timeout": 60,
"sse_read_timeout": 300
},
"server_name2": {
"transport": "sse",
"url": "http://127.0.0.1:8001/sse"
},
"server_name3": {
"transport": "streamable_http",
"url": "http://127.0.0.1:8002/mcp",
"headers": {},
"timeout": 60
},
"server_name4": {
"transport": "streamable_http",
"url": "http://127.0.0.1:8003/mcp"
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Dify Agent Mcp Sse?
Dify Agent Mcp Sse is a collection of agent strategies for Dify 1.0 that provides Function Calling and ReAct capabilities. It fetches and calls tools via the Model Context Protocol (MCP) using HTTP with SSE or Streamable HTTP transport.
How to use Dify Agent Mcp Sse?
Install the plugin via GitHub repository on the Dify plugin management page. Configure one or more MCP servers using a JSON object with fields such as transport (sse or streamable_http, default sse), url, headers, timeout, and sse_read_timeout. Optionally connect to managed MCP services from Composio, Zapier, or MCP.so.
Key features of Dify Agent Mcp Sse
- Supports Function Calling and ReAct agent strategies.
- Fetches and calls tools via MCP protocol.
- Uses HTTP with SSE or Streamable HTTP transport.
- Configurable multiple MCP services.
- Works with managed MCP providers (Composio, Zapier, MCP.so).
- Can be installed via GitHub or as an offline package.
Use cases of Dify Agent Mcp Sse
- Connecting to external MCP servers to execute tools within Dify agents.
- Using managed MCP services like Composio or Zapier to extend agent capabilities without self-hosting.
- Running Dify agents with custom MCP tool sets for specialized tasks.
- Offline deployment of Dify plugins with bundled dependencies.
FAQ from Dify Agent Mcp Sse
How to handle installation errors due to bad plugin signature?
Add the line FORCE_VERIFYING_SIGNATURE=false to your .env configuration file. This allows installation of plugins not listed in the Dify Marketplace.
How to install an offline version of the plugin?
Use the repackaging script from the GitHub repository dify-plugin-repackaging to download and repackage the plugin with all dependencies for offline use.
Frequently asked questions
How to handle installation errors due to bad plugin signature?
Add the line `FORCE_VERIFYING_SIGNATURE=false` to your `.env` configuration file. This allows installation of plugins not listed in the Dify Marketplace.
How to install an offline version of the plugin?
Use the repackaging script from the GitHub repository [dify-plugin-repackaging](https://github.com/junjiem/dify-plugin-repackaging) to download and repackage the plugin with all dependencies for offline use.
Basic information
More AI & Agents MCP servers
Solon Ai
opensolonJava AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

Transform MCP
UnstructuredThe Unstructured Transform MCP Server connects your ADK agent to Unstructured, a document processing platform that turns raw files into structured, AI-ready data. This integration gives your agent the ability to parse PD
21st.dev Magic AI Agent
21st-devIt's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic
MCP-NixOS - Because Your AI Assistant Shouldn't Hallucinate About Packages
utensilsMCP-NixOS - Model Context Protocol Server for NixOS resources
Hass-MCP
voskaControl and query Home Assistant from Claude and other LLMs — a Model Context Protocol (MCP) server.
Comments