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.
@iflytek
Basic information
This is a simple example of using MCP Server to invoke the task chain of the iFlytek SparkAgent Platform.
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>"
}
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
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.
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.
upload_file tool with a required file argument.uv or globally with uvx from GitHub.It accepts a file path and sends that file to the SparkAgent platform task chain. The exact behavior depends on the platform’s workflow.
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`).
The server supports stdio (default) and SSE. For SSE, run with `--transport sse --port 8000`.
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`.
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.

Amazon Seller Central MCP server. Connect Seller Central, Vendor Central and Amazon Ads to Claude, ChatGPT, Gemini or Cursor, and ask for net profit per SKU with your own COGS, VAT and FBM shipping costs, PPC down to the
Open-source Node.js FHIR MCP server with SMART Backend Services, metadata-aware search/CRUD tools, compact responses, FHIRPath filtering, safe pagination, audit events, and terminology lookup.
Detect and redact PII, PHI, PCI and secrets — SSNs, credit cards, passports, API keys and cloud credentials — in text and in local files, using the Strac DLP API. Five tools: redact_text, detect_sensitive_data, detect_fi

Tokenaissance is a online Personal Agent for Quant and Research investment available at https://tokenaissance.com.

OpenRouter for tools & data — 3,028 APIs for your agent, one token, pay per call. treg.to is a remote MCP server at https://treg.to/mcp/ that gives an agent 3,028 ready-to-call API endpoints across 82 platforms: SEO and
Comments