Ref
This MCP server provides AI assistants with access to technical documentation through Ref.tools, a specialized documentation search service that indexes APIs, frameworks, libraries, and other technical resources. Built with TypeScript using the Model Context Protocol SDK and axios, it offers three core tools: documentation search that queries curated technical docs with contextual relevance, web search as a fallback for broader queries, and URL reading that converts web pages to markdown for easy consumption. The implementation supports both legacy stdio transport and experimental streamable HTTP modes, requires a Ref API key for authentication, and can be configured to disable web search if users prefer alternative search providers, making it valuable for developers and AI coding assistants that need up-to-date, token-efficient access to technical documentation during development workflows.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- security
- Source
- PulseMCP
- Repository
- github.com/ref-tools/ref-tools-mcp
- Author type
- human
- Updated
- 2026-04-29
Use via MCP
Resolve Ref 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.