Postscript MCP server for your AI

No. This is a credential paste: the connect form asks for an API key, and you copy it from the Postscript dashboard at app.postscript.io → Account → API. Use the Private key, not the Public one; if none is shown, click Create Security Key Pair first. There is no OAuth app to register and no redirect URL to configure. The key you paste scopes the MCP server to a single store, and get_identity confirms which shop it belongs to.

It is for Postscript technical partners. A partner puts their partner key in API key and the target shop's Private API Key in Shop token, which PopMCP sends as the X-Postscript-Shop-Token header. A shop connecting its own account leaves it blank, and the header is never sent. With a shop token set, add_shop_to_trigger lets that shop use one of the partner's v1 Triggers in its Legacy Automations. Both values are stored encrypted and used server-side only.

Not directly. send_message delivers an SMS or MMS to an existing subscriber, so a new contact has to be added first. create_subscriber needs an opt-in keyword from get_keywords, and the subscriber it adds stays pending until they confirm the opt-in reply. Opt-outs stay explicit too: unsubscribe removes a subscriber from all Postscript messaging, and redact permanently erases their personal data for GDPR or CCPA, unsubscribing them as well.

Ask the agent for get_webhook_signing_token, which returns the signing token for the account, and check incoming payloads against it on your side. Before you go live, test_webhook sends a mock event to the callback_url subscribed to a webhook so you can confirm your endpoint handles it. If the endpoint moves or needs different headers, update_webhook changes the callback_url and custom headers by id without recreating the subscription.

Both, through different tools, because Postscript keeps the two systems separate and an event sent to one never reaches the other. create_custom_event starts or branches a Flow. For a shop still running Legacy Automations, fire_trigger fires a v1 Trigger for one subscriber and fills its merge tags from the data you pass; lookup_legacy_subscriber turns a phone number or email into the v1 subscriber id it needs, and get_trigger shows the merge tags. create_trigger, update_trigger, replace_trigger and delete_trigger manage the trigger definitions.

Not always. send_message creates a message request, and get_message_request shows whether it is processing, scheduled, sent or failed. Messages default to the promotional category, and a promotional send outside the subscriber's waking hours comes back scheduled; transactional and conversational sends need Postscript's approval. Once the request carries a sent_message, get_sent_message returns the final text, including the shop name Postscript adds to the front, and credits_used, which is what the send cost.

No. PopMCP hosts it and gives you a Streamable HTTP MCP URL. There is nothing to deploy, no callback URL to register, and no infrastructure to keep running or patch.

Any client that supports a remote Streamable HTTP MCP server: Claude Desktop, Claude Web, Claude Code, ChatGPT custom connectors, Codex and the Codex CLI, OpenCode and Z.ai's ZCode, as well as editors such as Cursor, Windsurf and Zed. Your client signs in to PopMCP with OAuth; the provider credential never leaves the server.

Connect Postscript in PopMCP first, then run claude mcp add --transport http popmcp https://app.popmcp.com/mcp in a terminal. Inside Claude Code, run /mcp and sign in to PopMCP in the browser window it opens, ticking Postscript on the consent screen. The Postscript tools are then available in that session, and no Postscript credential is stored on your machine.

Loading 29 tool definitions into every conversation burns context before the work starts. PopMCP loads a curated 18-tool set covering the everyday workflows and keeps the rest searchable, so your AI pulls a specialist tool only when a task needs it. Every tool stays searchable, and on Scale the owner can load the full catalog for a teammate's connection.

A tool is something your AI calls, and there are 29 here. A trigger is something PopMCP watches for you: 7 Postscript events that can start work on the PopMCP side. Triggers never enter your AI client's context, and none of them ask you to paste a callback URL into Postscript.