Houtini LM
Houtini LM is an MCP server that provides expert prompt engineering capabilities through LM Studio integration, featuring 35+ specialized functions for code analysis, generation, and creative tasks. Built with TypeScript and a modern plugin architecture, it offers intelligent context window management with automatic chunking for large codebases, comprehensive security validation with path traversal protection, and caching for performance optimization. The implementation includes analysis functions for code quality, security audits, and project structure evaluation, generation tools for unit tests, documentation, and WordPress themes, plus creative functions for games and CSS art generation. Designed for developers working with local AI models who need reliable, secure access to advanced prompting capabilities without cloud dependencies, it enables use cases like automated code review, documentation generation, security analysis, and rapid prototyping through Claude Desktop integration.
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/houtini-ai/houtini-lm
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Houtini LM 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.