ChangeEngine MCP: what's live, what's next

The communications inside one program, last edited first, each with its status, channel and who touched it last. Archived ones are left out.

The communications and surveys the account changed most recently, newest first. The fastest way to answer what is the team working on right now.

Search past communications by intent and get back resource links.

The order a person meets an account's communications, grouped by the date each one hangs off. This is how you see the shape of a journey, such as everything a new starter receives and when. Each line reads back in the same words set_schedule takes.

The whole review trail for one communication: each step, who took it, and the note. A changes-requested note is the answer to why something is not live yet.

Create an empty communication draft inside a program.

Rename a draft, rewrite its internal description, or move it into a different program, without touching its copy, audience or schedule.

Convert an existing message the way the app's own editor would, and get it back ready to edit. Pass a channel to move it there: work email, personal email, Slack, or SMS via Twilio. The content is converted for the new channel rather than rewritten, the sender falls back to that channel's default, and the email subject is cleared. Leave the channel out to keep it where it is. Either way a Markdown message becomes the editor's own format, which takes formatting Markdown cannot carry, such as alignment, color, buttons, columns and image sizes. Formatting the channel cannot show, such as a heading in chat, is kept as plain text, and anything the new channel cannot hold is dropped and listed. Edit what comes back and save it with set_message.

Target a named segment, an ad hoc segment expression composed from existing condition fields, a manager or manager's-manager expansion of a segment, or a Slack/Teams channel directly.

Override who the communication comes from, so a message can read as the People Team or a named person rather than the app. Pass null to fall back to the account default.

Every active segment, with a flag for which can act as a base segment.

Resolve a saved segment into the people it actually contains: a headcount, and the people themselves when you need them. Pass a channel and it splits that audience into who has a destination, who is missing one and who has opted out, so a thin audience shows up before anything is published rather than after. Available means a destination that is not opted out, which is not the same as guaranteed delivery. Saved segments only; an ad hoc segment expression is not resolved here.

Every merge tag this communication may use, grouped by the person it reads from, with the fallback each one carries. Not just names: department, job title, office, tenure fields, account-wide tags and every calendar event, plus the same fields read through manager and managers_manager. Which tags are valid depends on the audience, so set_audience first.

Postable Slack and Teams channels.

Get a one-time URL for uploading an image or a PDF straight to the file service at full quality, instead of passing its bytes through the conversation. It returns the upload command to run and the durable https:// URL the file will have once it lands, ready to drop into set_message or to hand to import_pdf. Pass an image URL to publish_image afterwards to also file it in the content library.

The tag names and folder paths in the library with a count against each, so you filter on something that actually exists.

The branded design templates an account can build from: posters, certificates, social posts, banners, TV displays, guides, FAQs, video call backgrounds, logos and manager one-pagers. Every layout is spelled out element by element, and the copy a layout already holds shows how long a replacement should be.

Create an editable design from a template with the copy and imagery already in place. It stays a real editable design rather than a flattened picture, so the team can keep working on it in the app afterwards.

Render a design with changes applied but not saved. This is the only way to see how replacement copy reflows before committing it, and it warns when text will shrink past legibility or an element would be pushed off the canvas.

Put a finished design into the content library, where the team can find it and render_content_library_template can carry it into a communication. Saving again refreshes the stored preview after an edit.

Search stock photography for a background or illustration the library has none of. Approved artwork from the content library comes first; this covers the gap.

The senders available to set_sender for a communication, and which one it currently uses.

See a communication rendered as its recipients will, with sample merge values, returned as an image. A tall message comes back as several images, top to bottom. This is the answer to a write that succeeds and still looks wrong.

Add, change, move and remove a survey's pages, questions and completion text in one call. Radiogroup, checkbox, dropdown, rating, boolean, text (12 input types) and long-form comment, with conditional display, answer-count validators, and completion text that varies by how someone answered. Every edit in a call is checked before any of it is saved, so a request that cannot be made in full changes nothing. Edits land on the draft revision, so respondents see nothing until launch_survey publishes it.

Save the completed translation set back onto the survey.

Stop a live survey taking answers, with your own message on the closed link. Answers already given stay, and launch_survey reopens it.

Non-archived surveys with status, response counts, and live links.

What people actually answered. Counts per answer for closed questions, open text tallied by theme, then whole responses so one person's rating and their comment read together. No answer is tied to a person and no identifier comes back; an anonymous survey shows nothing until 5 people have answered.

The same numbers for one individual send, most recent first, for the account, one program or one communication. Adds the channel, the segment, who published it, the trigger that fired it, clicks broken down by URL, errors broken down by reason, and the name and address of anyone it failed to reach. Everyone who opened, clicked or reacted also comes back by name, most engaged first, with the URLs each person clicked and how many times; a send names up to 50 of them and reports how many engaged people are not in the list. A hard bounce comes back with the full SMTP reason, so a bad address is finally actionable.

Why one named person did or did not get a communication. Give a work email address or an employee ID and it returns that person's own trail for that send: whether the communication was published at the time, whether they met the audience rules, which address it would use, whether the system had worked out how to reach them, and whether it put them in the queue. Queued is not proof of arrival, which is what read_delivery_forensics reports. The record covers the last 90 days and says the date it starts on.

The people the last employee sync could not place, because an existing person's work email or employee ID also arrived on a separate new HRIS record. The sync cannot tell which record is the person, so it removes them, and they receive nothing until the HRIS is corrected. Read this when someone is missing from an audience or has stopped receiving communications, before blaming the segment. The fix is in the HRIS, and the next sync places them again. An empty list means the last sync placed everyone it received.