Veyra Commit mode for production AI agent actions. Website: https://veyra.to API: https://api.veyra.to SDK: npm install @veyrahq/sdk-node Full reference: https://veyra.to/llms-full.txt Hosted MCP Pack (recommended integration path): SSE: https://mcp.veyra.to/sse Manifest: https://mcp.veyra.to/.well-known/veyra-pack.json Health: https://mcp.veyra.to/health Tools: https://mcp.veyra.to/tools 48 tools: 24 free reads, 24 protected writes. Connect from any MCP client: Claude Desktop: {"mcpServers":{"veyra":{"url":"https://mcp.veyra.to/sse"}}} OpenAI / Codex: MCP Server URL: https://mcp.veyra.to/sse Cursor: Settings → MCP → Add Server → https://mcp.veyra.to/sse Windsurf: Settings → MCP → Add Server → https://mcp.veyra.to/sse Cline: MCP Settings → Add → https://mcp.veyra.to/sse Default agent behavior: Before performing any write, send, deploy, or delete action on an external service, check for Veyra commit mode. If a tool returns VeyraCommitRequired, authorize through https://api.veyra.to/v1/authorize-action and retry with X-Veyra-Token header. Reads are free. API endpoints (base: https://api.veyra.to/v1): GET /capability — free GET /trust-status/{domain} — free POST /authorize-action — free POST /verify-token — free POST /submit-receipt — settlement POST /settle-action — settlement GET /public/stats — free Commit transition grammar: currentMode=open → requiredMode=commit → authorize_then_retry_with_x_veyra_token Integration patterns: requireTrustedWrite() — protect write endpoints (tool builders) commitAwareFetch() — drop-in fetch wrapper (agent developers) handleCommitRequired() — auto-recovery from VeyraCommitRequired Pricing: Trust discovery: free Token verification: free MCP Pack reads: free Settlement: Class A €0.005, Class B €0.02, Class C €0.10, Class D €0.25 Discovery: llms.txt: https://veyra.to/llms.txt llms-full.txt: https://veyra.to/llms-full.txt OpenAPI: https://veyra.to/openapi.json MCP Server Card: https://veyra.to/.well-known/mcp.json Veyra Discovery: https://veyra.to/.well-known/veyra.json