Integration · Marketing

Connect Claude & ChatGPT to AnnounceKit

Ask your AI to draft a changelog post, sum up what customers are asking for, or reply to a feature request in AnnounceKit. It can read and write changelog posts, feature requests, issues and knowledge base articles, read reader feedback and post statistics, and merge duplicate feature requests.

Connect AnnounceKit free

Free plan, no credit card. Takes about a minute.

Try asking

“Draft a changelog post about the new CSV export, and keep it as a draft.”
The AI creates the post with a title and body and leaves it as a draft, so nothing is published.
“What are the top feature requests right now?”
It lists feature requests sorted by TOP, with their status and labels.
“Reply to the dark mode request that we have started work on it.”
It posts your reply on the feature request.

What your AI can do

Changelog posts

Read, draft and update posts with labels, templates and segments, and read feedback and statistics.

Feature requests

List requests by TOP, TRENDING or NEW, read replies, comment and reply, create or update requests and merge duplicates.

Knowledge base and issues

List, create and update knowledge base articles and issues, with folders, labels and statuses.

“Merge these two requests about calendar sync.”
It merges one feature request into the other.
“How many views and clicks did our posts get last month?”
It reads post statistics for the date range: views, clicks and reactions.
“What did readers say about our last post?”
It lists the reader feedback left on that post.

23 tools for AnnounceKit

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

comment_on_feature_requestChanges dataAdd a comment (`content`) to a feature request (`feature_request_id`).
get_meChanges dataGet your own AnnounceKit user, your active project and your project memberships. Use it to find the project_id the other tools need.
get_postChanges dataGet one changelog post by `post_id` and `project_id`, with its contents, labels, draft status and dates.
get_post_statisticsChanges dataGet post analytics (views, clicks, reactions) for a date range (`input.start_date`/`end_date`), optionally per post, feed or widget.
get_projectChanges dataGet a project's details by `project_id`.
list_end_usersChanges dataList the end users AnnounceKit has seen in a project, sorted by last seen or name.
list_feature_request_repliesChanges dataList the replies on a feature request (`feature_request_id`).
list_feature_requestsChanges dataList feature requests in a project, with text, label, date and status filters, sorted by TOP, TRENDING or NEW.
list_issuesChanges dataList issues in a project, filtered by text `query`, labels or statuses.
list_kb_articlesChanges dataList knowledge base articles, filtered by text `query`, status, label or folder.
list_kb_foldersChanges dataList the knowledge base folders in a project (`project_id`).
list_labelsChanges dataList the labels you can put on posts in a project (`project_id`).
list_post_feedbackChanges dataList reader feedback on posts in a project, optionally for one post (`post_id`).
list_post_templatesChanges dataList the post templates in a project (`project_id`).
list_segmentsChanges dataList the audience segments defined in a project (`project_id`).
list_statusesChanges dataList the statuses issues can have in a project. Use to get a status_id.
list_team_membersChanges dataList the team members of a project (`project_id`).
merge_feature_requestsVisible to othersMerge one feature request (`merged_feature_request_id`) into another (`feature_request_id`).
reply_to_feature_requestChanges dataPost a reply (`content`, optional `subject`) on a feature request (`feature_request_id`).
save_feature_requestChanges dataCreate a feature request, or update one by passing `feature_request_id`: title, contents, labels, approved, archived or internal flags.
save_issueVisible to othersCreate an issue, or update one by passing `issue_id`: `title`, `status_id`, summary, labels and due date.
save_kb_articleChanges dataCreate a knowledge base article, or update one by passing `article_id`: `contents` (locale_id, title, body), folder, labels, draft flag and SEO fields.
save_postChanges dataCreate a changelog post, or update one by passing `post_id`: `contents` (locale_id, title, body per language), labels, `is_draft`, visible and expire dates. Setting is_draft false publishes it to your audience.

Set up in three steps

1
Pick the app
Create a free PipMCP account and choose AnnounceKit from the app list.
2
Paste your key
Paste your AnnounceKit API token. In AnnounceKit go to Settings > API Tokens (owners and managers only), create a token with Read or Write scope and copy it right away. It starts with ak_pat_ and is shown only once.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in AnnounceKit?

The AI can read your projects, posts, templates, labels, segments, statuses, feature requests and replies, knowledge base articles and folders, issues, end users, team members, reader feedback and post statistics. It can create and update posts, feature requests, issues and knowledge base articles, reply to and comment on feature requests, and merge feature requests.

Does the AI see my AnnounceKit credentials?

No. Your AnnounceKit credentials are encrypted at rest and never shown to the AI. After you save them, they are not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on, so you can start read-only. Publishing a post reaches your audience and a reply reaches the customer, so saving posts and replying can require your approval before they run. Merging requests can too. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT go to Settings › Apps & Connectors › Advanced and turn on Developer mode, then add your PipMCP link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

PipMCP has a free plan with no credit card required. Paid plans bill per completed task. You also need your own AnnounceKit account.

Should I create a Read or a Write token?

AnnounceKit tokens have a Read or Write scope. A Read token is enough to look at posts, feature requests, feedback and statistics. To draft posts, reply to requests or write articles, the AI needs a Write token. Only owners and managers can create tokens.