Prompts Library
This MCP server provides file-based prompt management with YAML frontmatter support for organizing and retrieving AI prompt templates. Built by tanker327 using TypeScript with gray-matter for metadata parsing and chokidar for real-time file watching, it stores prompts as markdown files with structured metadata including title, description, category, tags, difficulty level, and author information. The implementation features in-memory caching with automatic cache updates when files change, tools for adding prompts with automatic metadata generation, structured prompt creation with guided metadata input, and comprehensive CRUD operations for prompt collections. It's valuable for AI workflow automation, prompt library management, and team collaboration scenarios where users need to systematically organize, version, and share prompt templates across different AI applications and use cases.
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
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/tanker327/prompts-mcp-server
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Prompts Library 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.