Docs2Prompt
docs2prompt-mcp is an MCP server that wraps the docs2prompt library, allowing AI assistants to convert documentation from GitHub repositories or websites into LLM-friendly prompts. Developed by Andrew Melbourne, it builds on Reza Tabrizi's original library and exposes two main tools: one for fetching documentation from GitHub repos and another for retrieving documentation from URLs. The server handles authentication with GitHub via tokens and includes safeguards against oversized responses, making it particularly useful for developers who need to quickly reference or understand external codebases and documentation without leaving their conversation interface.
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
- version-control
- Source
- PulseMCP
- Repository
- github.com/melbourneandrew/docs2prompt-mcp
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve Docs2Prompt 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.