Skip the install. Get this working in under 2 minutes.
Start a free trial on cloud.anythingmcp.com, add the Zenkit in one click, then point your AI client (Claude, ChatGPT, Copilot or Cursor) at the generated MCP endpoint. No Docker, no git clone, zero engineering experience required.
Summary
Let your AI work in Zenkit: browse workspaces and collections, read fields, entries, members and activity, search everywhere, and create or update entries and post comments with your confirmation.
Try asking
Example prompts for Zenkit
Click any prompt to copy it. Paste into Claude, ChatGPT, Cursor, Gemini, Copilot or OpenClaw to run it against this connector.
Claude is AI and can make mistakes. Please double-check responses.
💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Zenkit, paste your credentials, mint an MCP API key and you're done. No Docker, no
git clone, no local server.
Zenkit + ChatGPT
Let your AI work in Zenkit: browse workspaces and collections, read fields, entries, members and activity, search everywhere, and create or update entries and post comments with your confirmation.
Prerequisites
See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:
ZENKIT_API_KEY
Step 1 — Get credentials
Setting up takes about 2 minutes and needs nothing but your Zenkit account.
- In Zenkit, click your avatar to open your profile and go to Integrations.
- Under API Key, generate a new key and copy it.
- Paste it into
ZENKIT_API_KEY, on its own, without spaces or a header name. - Install the connector and run
zenkit_get_current_user: it shows the user the key belongs to.
The key acts as you: it opens everything you can open in Zenkit, in every workspace. Generating a new key invalidates the old one, so the connector stops until you paste the new key. If the AI should only see some workspaces, use a separate Zenkit user that is a member of just those.
One API for all Zenkit apps: Zenkit Base, Zenkit To Do, Zenkit Projects and Hypernotes share the same data, so the same key reaches your to-do lists, project boards and databases.
How Zenkit is organised: a workspace holds collections (the API calls them lists), and a collection has fields and entries. Depending on the view, an entry is a task, a card, a row or a note. The AI starts with zenkit_list_workspaces_with_lists, reads the fields of a collection with zenkit_list_fields, and then pages through its entries 50 at a time, or searches by text across everything you can open.
What it reads: workspaces and their members, collections and who has access to them, fields with their type and label options, entries with every field value (title, text, numbers, dates, checkboxes, labels, assignees and linked entries), and the comments and change history of an entry or of a whole collection.
Asks before every change: zenkit_create_entry adds an entry, zenkit_update_entry changes field values (for labels, assignees and linked entries it can replace, add or remove values), and zenkit_comment_on_entry posts a comment in your name. These change shared data and can notify the people following the entry, so the AI shows you what will change and waits for your yes. Formula fields and the created and updated fields are read-only.
Switched off at install: zenkit_archive_entries. It moves entries to the archive, where they can be restored in the Zenkit app. An administrator can turn it on deliberately. No tool deletes anything for good.
Limits: Zenkit allows 200 requests a minute per user and 500 a minute per IP address. The AI prefers one filtered page over many single reads, and error D2 (Limit reached) means waiting a minute before trying again.
Common errors: 401 means the key is wrong or a newer key replaced it. 403 means you have no access to that workspace or collection. 404 means the id is unknown. C21 means Zenkit does not accept a parameter or field value, usually a field key that does not exist in that collection.
The connector does not create or change workspaces, collections or fields, upload files, set up webhooks, or restore archived entries.
Step 2 — Install the adapter
curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d
Step 3 — Add the connector in ChatGPT
Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (
https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide showsYOUR_SERVER_ID.
ChatGPT adds MCP servers as plugins on its Plugins page, on the web and on paid plans. Developer mode is no longer needed. In a Business workspace only admins and owners can add one; in Enterprise and Edu an admin can grant the Create plugins with MCPs permission.
- Go to chatgpt.com/plugins, click +, then Add custom MCP server.
- Enter a name, e.g. Name:
Zenkit. - Under Connection, enter the Server URL
https://cloud.anythingmcp.com/mcp/YOUR_SERVER_IDand keep Authentication on OAuth. - Select I understand and want to continue, then Create as a plugin. When ChatGPT asks, sign in to AnythingMCP and allow access.
- Install the new plugin from your personal plugins, then type @ in a chat and pick it.
Available tools
| Tool | What it does |
|---|---|
zenkit_get_current_user | Read the Zenkit user the API key belongs to: id, name, username, emails, locale and timezone |
zenkit_list_workspaces_with_lists | List every workspace the user can open, each with its collections (lists): ids, shortIds, uuids and names |
zenkit_get_workspace | Read one workspace with its name, description, settings and creation date |
zenkit_list_workspace_users | List the members of a workspace with user id, name and username |
zenkit_get_list | Read one collection (list) with its name, workspace, description and settings |
zenkit_list_list_users | List the users who have access to a collection (list), with user id, name and username |
zenkit_list_fields | List the fields (elements) of a collection: id, uuid, name, type (elementcategory), whether it is the primary title field, and for label… |
zenkit_filter_entries | List the entries (items) of a collection with all field values, page by page, optionally filtered |
zenkit_search_entries | Search entries by text across every workspace and collection the user can open |
zenkit_get_entry | Read one entry with all its field values, keyed by field uuid (for example <uuid>_text), plus displayString, comment count and dates |
zenkit_list_entry_activities | List the comments and change history of one entry, newest first, with total for paging |
zenkit_list_list_activities | List the comments and changes across a whole collection, newest first, with total for paging |
zenkit_create_entry | Create an entry (item) in a collection with the given field values |
zenkit_update_entry | Change field values of an entry |
zenkit_comment_on_entry | Post a comment on an entry as the API key's user |
zenkit_archive_entries | Delete entries of a collection by moving them to the archive (Zenkit's soft delete; they can be restored in the Zenkit app) |
Example prompts
- "Which open tasks in our Marketing collection are due this week, and who is assigned to them?"
- "Set the task Update pricing page to Done and add the label Website. Show me the change first."
- "Create an entry in our Bugs collection: Checkout button does not work in Safari, priority High, assigned to Lisa."
- "Search all my Zenkit workspaces for entries that mention the Müller project."
- "What changed in the Product Roadmap collection in the last 7 days, and who commented on what?"
FAQ
Does the free ChatGPT plan work with custom MCP servers? OpenAI documents custom MCP servers for paid plans only; the Free plan is not on its list.
Next steps
Was this guide helpful?
