Steel Puppeteer
This MCP server, developed by Steel, enables AI assistants to interact with web browsers through Puppeteer and Steel's browser automation platform. It provides tools for navigating web pages, taking screenshots, clicking elements, filling forms, and extracting content through a standardized interface. The implementation stands out by offering both local and cloud-based browser automation options, with built-in session management and console logging. By connecting AI capabilities with real browser interactions, this server empowers AI systems to perform complex web tasks, scrape data, and automate workflows. It is particularly useful for applications requiring web testing, data extraction, or any scenario where an AI assistant needs to interact with web content in a human-like manner.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- browser-automation
- Source
- PulseMCP
- Repository
- github.com/rdvo/mcp-server
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Steel Puppeteer from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.