SInstaller
This MCP server automates the installation and containerization of other MCP servers from GitHub repositories by analyzing codebases using LLM sampling, generating appropriate Docker configurations, and building ready-to-run container images. Built by semcp using Python with comprehensive GitHub integration, Docker service management, and intelligent repository analysis, it offers tools for installing MCP servers from GitHub URLs with automatic Dockerfile generation, updating existing installations with rebuilt images, managing containerized server lifecycles, and listing all installed servers with their configuration details. The implementation uses LLM-powered analysis to understand project structure and dependencies, automatically detects transport types (STDIO vs SSE), generates Docker build plans with proper environment variable handling, and provides complete MCP client configuration snippets for immediate integration, making it valuable for developers who want to quickly deploy and test multiple MCP servers without manual Docker setup or for organizations managing fleets of containerized MCP services.
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
- version-control
- Source
- PulseMCP
- Repository
- github.com/mossaka/mcp-sinstaller
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve SInstaller 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.