Prompt Engine
MCP server implementation by vasayxtx that provides dynamic prompt template management with Go template engine support, file system watching for real-time updates, and comprehensive CLI tooling for template rendering, validation, and listing. The implementation supports template partials, environment variable resolution, JSON argument parsing, and automatic prompt reloading when template files change, using fsnotify for file watching and the mark3labs/mcp-go library for MCP protocol handling. Built with Docker support and cross-platform releases via GoReleaser, it serves developers who need programmatic access to dynamic prompt generation with template inheritance, teams building AI applications requiring structured prompt management with live reloading capabilities, and organizations needing Git workflow automation through specialized commit message generation templates with conventional commit format support.
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 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
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/vasayxtx/mcp-prompt-engine
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Prompt Engine 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.