English Français العربية

Audryo

Registre officiel Santé

Lifecycle email for agents: journeys, campaigns, contacts, consent and delivery health.

Code source Site web Documentation

Installation

Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).

Remote (streamable-http)
Claude Code 
claude mcp add --transport http audryo 'https://mcp.audryo.com/mcp'
Configuration JSON (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "audryo": {
            "type": "http",
            "url": "https://mcp.audryo.com/mcp"
        }
    }
}

Documentation

Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.

Sommaire
  1. Audryo agent toolkit
  2. Safety model
  3. Quick start
  4. Configuration
  5. MCP tools
  6. CLI
  7. Skills
  8. Contributing

Audryo agent toolkit

Let your AI agent run your lifecycle email: audiences, journeys, campaigns, emails and transactional sends in Audryo, through the same API the app uses. Your agent does the setup work; nothing reaches a customer until a person approves it.

This repo ships the audryo CLI, an MCP server and agent skills for Claude Code, Codex, Cursor and any other MCP client.

You:   Set up an onboarding journey for signups who haven't created a
       project after 3 days.

Agent: Reads your data schema, builds the audience, drafts a three-email
       journey, dry-runs it and fast-forwards it in the sandbox. Then it
       hands back what to review. Nothing has been sent.

Safety model

  • Drafts by default. Journeys, emails and campaigns an agent creates are review-only proposals.
  • Sending needs deliver. Without that scope a key cannot activate a journey or send anything, even by mistake. With it, Audryo still requires a passing dry run and confirmed emails.
  • Sandbox first. New projects capture every email in a sandbox inbox, so agents can test real journeys end to end. Going live is a human decision in the app.
  • Retry-safe. Sends and proposals take an Idempotency-Key, so a retried call never sends twice.
  • No inferred consent. Ingesting contacts never grants marketing consent.

Quick start

  1. Sign up (free during the public beta) and create a project. It starts in the sandbox.
  2. Create an API key under Settings → Developer with the smallest scope that works (see Configuration).
  3. Connect your agent:
Claude Code (plugin: MCP server + skills)
export AUDRYO_API_KEY="sf_live_..."
claude plugin marketplace add Audryo/agent-toolkit
claude plugin install audryo@audryo
Any agent: skills only
npx skills add Audryo/agent-toolkit
Any MCP client
{
  "mcpServers": {
    "audryo": {
      "command": "npx",
      "args": ["-y", "audryo", "mcp"],
      "env": {
        "AUDRYO_API_KEY": "sf_live_...",
        "AUDRYO_PROJECT_ID": "<project-uuid>"
      }
    }
  }
}

Codex: codex mcp add audryo --env AUDRYO_API_KEY=sf_live_... -- npx -y audryo mcp

Configuration

VariableRequiredDefault
AUDRYO_API_KEYyes—
AUDRYO_PROJECT_IDfor project toolslist with npx audryo bootstrap
AUDRYO_API_BASEnohttps://api.audryo.com/v1

Give agents the smallest key that works:

TaskScopes
Inspectread
Sync data, draft journeys, emails and campaignsread, write
Activate journeys, send campaigns and transactional emailread, write, deliver

MCP tools

AreaToolsScope
Orientget_manifest, get_bootstrap, get_setup_context, get_brief, get_plan_usageread
Product and dataget_product_context, get_data_context, list_contacts, ingest_contacts, ingest_eventsread / write
Audienceslist_audiences, get_audience, preview_audience, create_audience, update_audience, delete_audience, suggest_audiencesread / write
Journeyslist_journeys, inspect_journey, create_journey_proposal, revise_journey, propose_from_finding, run_dry_runread / write
Emailscreate_email, create_journey_emailwrite
Campaignslist_campaigns, draft_campaignread / write
Sandboxget_delivery_mode, list_sandbox_messages, get_sandbox_message, fast_forward_journeyread / write
Insightsget_delivery_health, get_performance, get_observation, run_observation, get_copilot_planread
Go liveactivate_journey, pause_journey, send_campaign, send_transactionaldeliver

Every tool is also a CLI command.

CLI

npx audryo bootstrap
npx audryo contacts ingest contacts.json
npx audryo events ingest events.json
npx audryo journeys list
npx audryo journeys inspect <workflowId>
npx audryo audiences create --name "All contacts" --definition '{"operator":"and","conditions":[]}'
npx audryo campaigns draft --name "July update" --audience-id <id> --subject "What's new"
npx audryo delivery health

Skills

SkillTeaches the agent to
audryo-apiConnect, pick scopes, use MCP or CLI instead of curl, stop at review
audryo-emailBuild valid email documents, handle locales, save drafts for review
audryo-sendingChoose communication classes, respect consent, protect deliverability

Full guide: https://app.audryo.com/docs/agents/quickstart

Contributing

Issues and pull requests are welcome. See CONTRIBUTING.md and the changelog. Report security issues privately: SECURITY.md.

License: MIT

Questions fréquentes

Qu'est-ce que Audryo ?

Lifecycle email for agents: journeys, campaigns, contacts, consent and delivery health.

Comment installer Audryo ?

Il fonctionne comme serveur distant. Dans Claude Code : claude mcp add --transport http audryo 'https://mcp.audryo.com/mcp'. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.

Faut-il une clé API pour Audryo ?

Son entrée au registre n'indique aucune clé ni secret obligatoire. Certaines fonctions peuvent tout de même demander un compte auprès du service auquel il se connecte.

Audryo est-il open source ?

Oui. Son code est sur GitHub sous licence MIT.

Qui maintient Audryo ?

Il est publié par Audryo. AI.tn le référence sans le maintenir ni le recommander.

Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.