Limited Beta AccessThe first MCP-native autonomous revenue operating system.

Engineering blueprint

Architecture.

The full blueprint of Pyxym's autonomous revenue infrastructure. AgenticCore orchestration, NuclearPolicyEngine governance, public MCP endpoint, post-to-invoice attribution.

Diagrams inline

Architecture at a glance.

Authentication flows

Three auth modes : Bearer ApiKey (Stripe pattern, default), OAuth client_credentials (M2M), OAuth password grant (legacy, deprecated). Identity store enforces workspace context + scopes per request.

ClientPyxym APIIdentity StoreA · Bearer ApiKeyAuthorization: Bearer pyx_live_xxxverify key + scopesworkspace context200 OK + RateLimit headersB · OAuth client_credentialsPOST /oauth/tokenaccess_token + expires_inC · OAuth password (legacy)username + passwordaccess_token + refresh_token

Webhook delivery

Outbox pattern : every resource mutation writes a webhook row in same transaction. Delivery worker picks rows, signs payload HMAC SHA-256, posts to customer endpoint. Exponential retry 7× over 32h on non-2xx.

Resource mutationagent_post.publishedWebhook dispatcherqueue insert · outbox rowDelivery workerpick · sign HMAC SHA-256Customer endpointverify sig · 2xxExponential retry · 7× over 32h on non-2xx

Streaming SSE flow

Native token-by-token streaming via Server-Sent Events. X-Accel-Buffering: no disables nginx buffering. Events : meta.start (request_id + model), content.delta (tokens), meta.complete (usage + finish_reason).

ClientPyxym APILLM providerPOST /v1/posts/generate/streamX-Accel-Buffering: no · Content-Type: text/event-streamevent: meta.startdata: { request_id, model }upstream LLM streamevent: content.delta (token by token)event: meta.complete + usage

Workspace hierarchy + permissions

Organization owns billing + SSO + admin policy. Multiple workspaces per organization (sandbox + live per workspace). Five role-based permissions sets : admin, operator, analyst, developer, guest.

Organizationbilling · SSO · adminsWorkspace · Salessandbox + liveWorkspace · Marketingsandbox + liveWorkspace · CSsandbox + liveRole-based permissionsadminall scopesoperatoragents + postsanalystread + reportsdeveloperAPI keys + MCPguestread-only sandbox

Sandbox vs Live isolation

Strict separation : sandbox keys (pyx_test_*) only access sandbox DB schema with mock connectors and no real outbound traffic. Live keys (pyx_live_*) target production DB with audit trail and real connectors. No cross-tier reads ever.

SANDBOX TIER · pyx_test_Sandbox API keysIsolated DB schemaMock connectors · no real sendfree · no SLA · auto-purge 30dSTRICT WALLLIVE TIER · pyx_live_Live API keysProduction DB · audit trailReal connectors · attributed revenuepaid plan · SLA 99.9 · immutable

MCP architecture

Native Model Context Protocol endpoint at mcp.pyxym.ad. 12 AI clients (Claude Desktop, Cursor, Windsurf, ChatGPT Dev, Gemini CLI, Mistral Le Chat, Claude Code, Cline, Zed, JetBrains, VS Code Copilot, Continue.dev) connect via Streamable HTTP with Bearer ApiKey, access 43 tools + 8 resources + 5 prompts mapped to the Pyxym API V2.

12 AI clients
AnthropicClaude Desktop
AnthropicClaude Code
CursorCursor
WindsurfWindsurf
OpenAIChatGPT Dev
Google GeminiGemini CLI
Mistral AIMistral Le Chat
ClineCline
Zed IndustriesZed
Continue.dev
JetBrainsJetBrains
GitHub CopilotVS Code Copilot
MCP server
mcp.pyxym.ad
TLS A+ rated
43 Tools
posts · agents · sales · revenue
8 Resources
mission control · brand DNA · audit
5 Prompts
orchestration scaffolds
Pyxym backend
Autonomous Revenue Stack
  • AgenticCore
  • NuclearPolicyEngine
  • Decision Loop
  • Revenue Engine
  • SMA Surfaces

All MCP calls authenticated · audited via Decision Audit Center · workspace-scoped

Decision Loop architecture

CanonicalOrchestratorService injects 12 context signals into 8 sub-agents (Strategy, Planner, Creative, Critic, Risk, Revenue, Memory, Orchestrator), produces outputs (posts, conversations, conversion flows, policy decisions), and closes the loop via 5 bayesian feedback channels. 5 autonomous crons keep the system recalibrating without human input.

12 Context signalsInbound DMMarket intelDaily briefingMission ControlSales pipelineConnector healthTrust thresholdsKPI signalsCreative historyLab experimentsFunnel stateRevenue attributionDecision Loop cycleCanonicalOrchestratorServiceorchestrate(agent) · inject 12 signals · run sub-agentsStrategyPlannerCreativeCriticRiskRevenueMemoryOrchestr.OutputsPost publishedConversation replyConversion flowQuote / invoicePolicy decisionAudit entry5 Bayesian feedback loopsmarket intel · sales attribution · revenue · viral · creative patterns5 Autonomous cronsmi-auto-rescan · auto-react-to-briefing · connector-degradation · trust-degradation-watch · creative-pattern-mining
Documentation

Engineering deep-dives ship at docs.pyxym.ad.

The complete architecture documentation — every flow, every endpoint, every governance contract — lives in our production docs site. Mermaid diagrams, sequence flows, schema definitions, and replay walkthroughs.

View full architecture documentation

For detailed implementation specs and code examples, visit docs.pyxym.ad.

Public MCP endpoint
Live

mcp.pyxym.ad

Native Model Context Protocol endpoint — connect from Claude Desktop, Cursor, ChatGPT Dev Mode, Windsurf, and 8 more AI clients. 43 tools · 8 resources · 5 prompts. TLS A+ rated by SSL Labs.