iFly-Spark-Agent-MCP Server
Connect AI assistants to the iFlytek SparkAgent Platform via MCP for file management, workflow automation, and easy integration with FlowHunt.

What does “iFly-Spark-Agent-MCP” MCP Server do?
The iFly-Spark-Agent-MCP MCP Server is a simple example implementation that connects AI assistants to the iFlytek SparkAgent Platform using the Model Context Protocol (MCP). This server acts as a bridge, allowing AI clients to invoke task chains on the SparkAgent Platform through a standardized interface. By exposing tools such as file upload, it enables seamless AI integration for tasks such as file management, process automation, and workflow orchestration. The server is designed to enhance development workflows by facilitating communication between AI assistants and the SparkAgent’s capabilities, making it easier for developers to add advanced functionality to their applications.
List of Prompts
No prompt templates are mentioned in the repository.
List of Resources
No explicit resources are listed or described in the repository.
List of Tools
- upload_file
Allows clients to upload a file by specifying the file path. This tool exposes file management capabilities to AI clients, enabling them to send files to the SparkAgent Platform for further processing or workflow execution.
Use Cases of this MCP Server
- File Upload and Management
Developers can use theupload_file
tool to transfer local files to the SparkAgent Platform, automating file-based workflows or initiating processing pipelines. - Task Chain Invocation
The server enables AI clients to trigger task chains on the SparkAgent Platform, streamlining complex operations that require orchestrating multiple steps or services. - Integration with AI Development Tools
By supporting MCP, the server can be integrated with AI development environments like Claude, Cursor, and Windsurf, making it easier to connect AI applications with SparkAgent’s capabilities. - Automated Workflow Execution
Developers can automate repetitive tasks or batch processes by invoking SparkAgent workflows programmatically through the MCP server interface.
How to set it up
Windsurf
No specific instructions found for Windsurf.
Claude
- Ensure prerequisites:
- Install Node.js and
uv
oruvx
. - Clone or download the iFly-Spark-Agent-MCP repository.
- Install Node.js and
- Locate and open
claude_desktop_config.json
ormcp.json
. - Add the server using either method:
Using uv:
{
"mcpServers": {
"ifly-spark-agent-mcp": {
"command": "uv",
"args": [
"--directory",
"/path/to/ifly-spark-agent-mcp",
"run",
"ifly-spark-agent-mcp"
],
"env": {
"IFLY_SPARK_AGENT_BASE_URL": "xxxx",
"IFLY_SPARK_AGENT_APP_ID": "xxxx",
"IFLY_SPARK_AGENT_APP_SECRET": "xxxx"
}
}
}
}
Using uvx with GitHub repository:
{
"mcpServers": {
"ifly-spark-agent-mcp": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/iflytek/ifly-spark-agent-mcp",
"ifly-spark-agent-mcp"
],
"env": {
"IFLY_SPARK_AGENT_BASE_URL": "xxxx",
"IFLY_SPARK_AGENT_APP_ID": "xxxx",
"IFLY_SPARK_AGENT_APP_SECRET": "xxxx"
}
}
}
}
- Save the configuration file and restart Claude.
- Verify the setup by listing available tools or executing a test command.
Securing API Keys
Store sensitive keys in the env
section:
"env": {
"IFLY_SPARK_AGENT_BASE_URL": "xxxx",
"IFLY_SPARK_AGENT_APP_ID": "xxxx",
"IFLY_SPARK_AGENT_APP_SECRET": "xxxx"
}
Cursor
No specific instructions found for Cursor.
Cline
No specific instructions found for Cline.
How to use this MCP inside flows
Using MCP in FlowHunt
To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:
{
"ifly-spark-agent-mcp": {
"transport": "streamable_http",
"url": "https://yourmcpserver.example/pathtothemcp/url"
}
}
Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “ifly-spark-agent-mcp” to match your actual server name and URL.
Overview
Section | Availability | Details/Notes |
---|---|---|
Overview | ✅ | Overview provided in README and description |
List of Prompts | ⛔ | No prompt templates found |
List of Resources | ⛔ | No resources listed |
List of Tools | ✅ | upload_file described in README |
Securing API Keys | ✅ | Uses env section in configuration example |
Sampling Support (less important in evaluation) | ⛔ | No sampling support mentioned |
Based on the available documentation, this MCP server provides only basic functionality, primarily centered around one tool (upload_file
). It includes straightforward setup guidance and proper license information, but lacks advanced features, prompt templates, and resource definitions. Its scope is limited but clear, ideal as a minimal working example. Overall, it rates low to moderate for versatility and depth.
MCP Score
Has a LICENSE | ✅ (MIT) |
---|---|
Has at least one tool | ✅ |
Number of Forks | 3 |
Number of Stars | 1 |
Frequently asked questions
- What is the iFly-Spark-Agent-MCP Server?
It is an MCP server that connects AI assistants to the iFlytek SparkAgent Platform, enabling features like file upload, task chain invocation, and workflow orchestration through a standardized protocol.
- What tools does this MCP server provide?
Currently, it provides the `upload_file` tool, allowing clients to upload files for management or further processing on the SparkAgent Platform.
- How do I configure the iFly-Spark-Agent-MCP server in FlowHunt?
Add the MCP component in your FlowHunt workflow, then enter your MCP server details using a JSON configuration like: { "ifly-spark-agent-mcp": { "transport": "streamable_http", "url": "https://yourmcpserver.example/pathtothemcp/url" } } in the system MCP configuration section.
- How are API keys and credentials secured?
API keys and credentials are stored in the `env` section of the configuration, keeping sensitive data out of source files and ensuring secure integration.
- Can I integrate this server with other AI development tools?
Yes, the server can be used with Claude, Cursor, Windsurf, and other tools that support MCP, making it flexible for various AI development workflows.
Integrate iFly-Spark-Agent-MCP with FlowHunt
Enhance your AI development workflow by connecting FlowHunt with the iFly-Spark-Agent-MCP Server for seamless file uploads and automated task chains.