dkedar7/streamlit-mcp

Developer tools

このページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。原文を見る

2 stars 7 forks 品質 80 トレンド 28MIT

Repository Install

Serve any Streamlit app as an MCP server — agents drive it natively, no browser automation.

概要

Agents introspect your app's widgets, set values, click buttons, and read the rendered output and session_state — natively, over MCP, with . 📖 https://dkedar7.github.io/streamlit-mcp/ 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 , not pixels. Gradio and Dash already shipped native app-as-MCP; this fills the Streamlit gap. 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: The app a human runs What the agent sees over MCP A human can also watch the agent work 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. — add to your MCP config (claude_desktop_config.json or .

README

以下は原文 README の抜粋です。原文を見る。

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

Tool	What it does
`list_widgets` / `get_layout`	introspect widgets (kind, label, value, constraints, whether it’s `disabled`)
`set_widget(identifier, value)`	set a widget and rerun
`click(identifier)`	click a button and rerun
`read_output()`	the rendered element tree, agent-readable
`get_state()`	the app’s `session_state`

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

GitHub で README 全文を見る

インストール

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

MCP 初心者？mcpskill.org のガイドから始めましょう →

設定

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