Web and Python Sandbox
MCP Server provides tools for AI assistants to access web content and execute Python code in a sandboxed environment. Built by Tom Foster, it implements both web and Python tools over the Model Context Protocol, supporting both stdio and Server-Sent Events (SSE) transports. The web tool can convert HTML to markdown, extract links, or retrieve raw content, while the Python tool executes code with appropriate resource limits and security constraints. The implementation is containerized with Docker, includes comprehensive testing, and is particularly valuable for AI assistants that need to verify information online or demonstrate working code examples.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- cloud-infra
- Source
- PulseMCP
- Repository
- github.com/tcpipuk/mcp-server
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve Web and Python Sandbox 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.