ifly-spark-agent-mcp

@iflytek

About ifly-spark-agent-mcp

This is a simple example of using MCP Server to invoke the task chain of the iFlytek SparkAgent Platform.

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "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": "<YOUR SERVER HOST>",
        "IFLY_SPARK_AGENT_APP_ID": "<YOUR APP ID>",
        "IFLY_SPARK_AGENT_APP_SECRET": "<YOUR APP SECRET>"
      }
    }
  }
}

Tools

No tools detected

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is ifly-spark-agent-mcp?

ifly-spark-agent-mcp is a simple MCP server that invokes task chains on the iFlytek SparkAgent Platform. It exposes a single tool, upload_file, and is intended for developers using MCP clients (like Claude) to interact with SparkAgent workflows.

How to use ifly-spark-agent-mcp?

Start the server locally with uv run ifly-spark-agent-mcp (stdio transport) or pass --transport sse --port 8000 for SSE transport. For persistent use with Claude, add a configuration to claude_desktop_config.json using uv or uvx, setting the required environment variables: IFLY_SPARK_AGENT_BASE_URL, IFLY_SPARK_AGENT_APP_ID, and IFLY_SPARK_AGENT_APP_SECRET.

Key features of ifly-spark-agent-mcp

Exposes a single upload_file tool with a required file argument.
Supports both stdio and SSE transports.
Runs locally with uv or globally with uvx from GitHub.
Designed as a minimal example for MCP + SparkAgent integration.
Easy to configure in MCP-compatible clients like Claude.

Use cases of ifly-spark-agent-mcp

Upload a local file to a SparkAgent task chain from an MCP client.
Prototype MCP integrations with iFlytek’s SparkAgent Platform.
Provide a reusable recipe for building custom SparkAgent MCP servers.

FAQ from ifly-spark-agent-mcp

What does the `upload_file` tool do?

It accepts a file path and sends that file to the SparkAgent platform task chain. The exact behavior depends on the platform’s workflow.

How do I configure the environment variables?

Set IFLY_SPARK_AGENT_BASE_URL, IFLY_SPARK_AGENT_APP_ID, and IFLY_SPARK_AGENT_APP_SECRET in the MCP client’s configuration (e.g., env block in claude_desktop_config.json).

What transport options are available?

The server supports stdio (default) and SSE. For SSE, run with --transport sse --port 8000.

Where can I get the server code?

The code is hosted on GitHub. You can run it directly with uvx --from git+https://github.com/iflytek/ifly-spark-agent-mcp ifly-spark-agent-mcp.

Is this server production-ready?

No – the README presents it as a simple example to demonstrate invoking SparkAgent task chains via MCP. It is not a full-featured production server.

Frequently asked questions

What does the `upload_file` tool do?

It accepts a file path and sends that file to the SparkAgent platform task chain. The exact behavior depends on the platform’s workflow.

How do I configure the environment variables?

Set `IFLY_SPARK_AGENT_BASE_URL`, `IFLY_SPARK_AGENT_APP_ID`, and `IFLY_SPARK_AGENT_APP_SECRET` in the MCP client’s configuration (e.g., `env` block in `claude_desktop_config.json`).

What transport options are available?

The server supports stdio (default) and SSE. For SSE, run with `--transport sse --port 8000`.

Where can I get the server code?

The code is hosted on GitHub. You can run it directly with `uvx --from git+https://github.com/iflytek/ifly-spark-agent-mcp ifly-spark-agent-mcp`.

Is this server production-ready?

No – the README presents it as a simple example to demonstrate invoking SparkAgent task chains via MCP. It is not a full-featured production server.

Comments

Basic information

More AI & Agents MCP servers

欢迎来到智言平台

Shy2593666979

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

797