streamlit-mcp

Serve any Streamlit app as an MCP server. Agents introspect your app’s widgets, set values, click buttons, and read the rendered output and session_state — natively, over MCP, with no browser automation.

📖 Documentation:

pip install streamlit-mcp          # or run with no install via: uvx streamlit-mcp ...

# serve an app over MCP (stdio for local clients)
streamlit-mcp serve app.py
# ...or HTTP/SSE on loopback for local networked agents
streamlit-mcp serve app.py --transport http --port 8000

# drive it yourself from the terminal (same engine the agent uses)
streamlit-mcp inspect app.py
streamlit-mcp call app.py --set "Name=agent" --click "Save" --read

Streamlit has no callback graph — it reruns the whole script per interaction — so streamlit-mcp drives the app headlessly through Streamlit’s own test runtime (streamlit.testing.v1.AppTest) and returns the semantic element tree, not pixels. Gradio and Dash already shipped native app-as-MCP; this fills the Streamlit gap.

Demo

A normal Streamlit app (what a human opens in a browser) and what an agent does with the same app over MCP — inspect the widgets, call to set values / click / read the result. No browser:

A human can also watch the agent work live in their browser — no refresh, no browser automation — by opting in with one with block (from streamlit_mcp.live import live). See the live / human-in-the-loop guide.

Use it with an MCP client

Claude Desktop / Cursor — add to your MCP config (claude_desktop_config.json or .cursor/mcp.json):

{
  "mcpServers": {
    "streamlit-mcp": {
      "command": "uvx",
      "args": ["streamlit-mcp", "serve", "/absolute/path/to/your/app.py"]
    }
  }
}

Claude Code:

claude mcp add streamlit-mcp -- uvx streamlit-mcp serve /absolute/path/to/your/app.py

uvx runs the published package with no prior install. stdio (the default) is the right transport for local clients.

Tools exposed to agents

Supported widgets: text_input, number_input, text_area, slider, select_slider, selectbox,