MCPML Browser Recorder
@a5c-ai
MCPML Browser Recorder について
Browsing Session Recorder MCP Server (powered by MCPML and playwright)
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"mcpml-browser-recorder": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/a5c-ai/mcpml#egg=mcpml",
"mcpml",
"run",
"-c",
"https://github.com/a5c-ai/mcpml-browser-recorder.git",
"--transport=sse"
]
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is MCPML Browser Recorder?
A Model Context Protocol server that records browser sessions using the MCPML framework. It provides a single tool, record_session_agent, for capturing a browsing session. Aimed at developers who need to automate or replay browser interactions.
How to use MCPML Browser Recorder?
Run the server using uvx with the mcpml CLI: uvx --from git+https://github.com/a5c-ai/mcpml#egg=mcpml mcpml run -c https://github.com/a5c-ai/mcpml-browser-recorder.git --transport=sse. Alternatively, clone the repository, run the dependency installer, and then run the server locally.
Key features of MCPML Browser Recorder
- Records a browser session via the
record_session_agenttool. - Operates over SSE (Server-Sent Events) transport.
- Integrates with the MCPML runtime for execution.
Use cases of MCPML Browser Recorder
- Capturing user interaction flows for testing or replay.
- Automating session recording in a development or debugging workflow.
- Logging browser behavior for analysis or compliance.
FAQ from MCPML Browser Recorder
—
「ブラウザ自動化」の他のコンテンツ
Firecrawl Mcp Server
mendableai🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
Webpage Screenshot MCP Server
ananddtyagiAn MCP that gives your agent the ability to snap a screenshot of webpages. Useful when you want your agent to check its progress during development.
browser-use-mcp-server
co-browserBrowse the web, directly from Cursor etc.
Fastcrw
usFast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary.

Puppeteer
modelcontextprotocolModel Context Protocol Servers
コメント