Docy (Documentation Access)
Docy is an MCP server that provides AI assistants with direct access to technical documentation from configured sources. Built by Oliver Borchers, it uses crawl4ai to scrape documentation websites and diskcache for efficient caching, enabling LLMs to search, retrieve, and navigate through documentation content without leaving the conversation context. The server features hot-reload support for documentation sources, intelligent caching to reduce latency, and can be deployed as a shared SSE server across multiple projects. Particularly valuable for developers who need accurate, real-time documentation access during coding sessions, Docy helps eliminate outdated information and broken links when working with technical frameworks and libraries.
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
- devops-ci
- Source
- PulseMCP
- Repository
- github.com/oborchers/mcp-server-docy
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Docy (Documentation Access) 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.