Snippets
Stores, searches, and manages code snippets using AI-powered semantic search combined with traditional keyword matching. Built using the Xenova/all-MiniLM-L6-v2 model for vector embeddings, it provides tools for adding snippets with automatic language detection, updating and deleting snippets with re-embedding when needed, and hybrid search that combines semantic similarity (70% weight) with keyword matching (30% weight) across code, descriptions, tags, and language fields. The implementation uses JSON-based storage with cached embeddings for fast retrieval, supports filtering by tags, language, and date ranges, and requires no external database setup.
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
- database
- Source
- PulseMCP
- Repository
- github.com/freakynit/snippets-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Snippets 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.