Regira docs, on tap for AI agents.
This is a hosted Model Context Protocol server for the Regira libraries — the .NET packages on nuget.org and the @regira/modules front-end library on npm. Connected agents can search the documentation, fetch per-package setup guides and code examples, and scaffold entities end-to-end.
It speaks MCP over streamable HTTP — there is nothing to browse here. Point your client at:
https://mcp.regira.com/mcp
Claude Code and GitHub Copilot (VS Code) both read a .mcp.json at your
repo root (approve / trust the server the first time it starts):
{
"mcpServers": {
"regira": {
"type": "http",
"url": "https://mcp.regira.com/mcp"
}
}
}
Or, for Claude Code only, one command:
claude mcp add --transport http regira https://mcp.regira.com/mcp
Claude Desktop / claude.ai — Customize → Connectors → + Add → Add custom connector,
name regira, URL above; on Team and Enterprise an Owner adds it under Organization settings → Connectors
(there is no config file to edit).
GitHub Copilot (VS Code) — the .mcp.json above; then enable the Regira tools under
Configure Tools in the Chat view.
Cursor — the same JSON in .cursor/mcp.json.
Then ask your agent to build something — it starts from get_bootstrap_guide and works through the
checkpoints. Nine sample apps were generated this way.
Free tier: no key, no sign-up. The server allows 30 requests per minute per client; a
Regira license key sent as the X-License-Key
header removes that limit. The Regira Entities packages themselves are free up to 5 simple + 2 complex entity
registrations per application.