HAL (HTTP API Layer)
This MCP server provides HTTP API capabilities to Large Language Models through OpenAPI/Swagger integration, enabling dynamic tool generation from API specifications with comprehensive secrets management and URL restrictions. Built by Dean Ward using TypeScript with Zod validation, it offers standard HTTP methods (GET, POST, PUT, PATCH, DELETE, HEAD, OPTIONS) with secret substitution using {secrets.key} syntax, namespaced secrets with URL pattern restrictions for enhanced security, and automatic documentation search tools for API exploration. The implementation features intelligent secret loading from HAL_SECRET_ environment variables, URL validation against allowed patterns, OpenAPI spec parsing for automatic tool registration, and specialized presentation component support, making it valuable for integrating AI assistants with existing APIs, managing secure API credentials across multiple services, and building AI tools that need programmatic access to REST APIs without manual HTTP client configuration.
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
- security
- Source
- PulseMCP
- Repository
- github.com/deanward/hal
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve HAL (HTTP API Layer) 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.