Kontent.ai MCP server
Kontent.ai in any MCP client, through Memtro: Kontent.ai does not publish this server. Memtro's Kontent.ai connector reads Kontent.ai through its API with the credentials you connect, and one endpoint hands those tools, every other system you connect and Memtro's memory tools to Claude Code, Cursor, Claude Desktop or anything else that speaks Streamable HTTP, as you.
What the model can do
Kontent.ai headless CMS: content items with their type, collection and last change, one item's language variants with workflow step, schedule and the text of every element, the latest variants of a content type, content types and their elements, languages, workflows and steps, and assets; when you ask, can create or rename an item, set text elements of a draft variant, move a variant to a workflow step, create a new version of a published variant, publish or unpublish now or on a schedule, cancel a schedule, and delete a variant, an item or an unused asset.
Reads
kontent_itemsContent items (the wrappers whose words live in language variants): name, codename, content type, collection, external id and last change.kontent_itemOne content item with its language variants: workflow step, last change, publish and unpublish schedule, due date…kontent_variants_by_typeThe latest variant (draft over published) of every item of one content type, with workflow step, last change, schedule and element values.kontent_typesContent types with their elements (codename, name, type: text, rich_text, asset, modular_content, taxonomy …) and last change.kontent_languagesLanguages in the environment: id, name, codename, whether active and default, and its fallback language.kontent_workflowsWorkflows and their steps in order (id, name, codename and which steps each can move to), with the Published, Scheduled and Archived steps.kontent_assetsAssets (images and files): title, file name, type, size, dimensions, URL and last change.
Acts, when you ask
These change something in Kontent.ai. The model is told to use them only when you ask for exactly that, and each one is granted by name: per team on a shared connection, by the owner on a personal one.
kontent_create_itemCreates a content item of a content type in Kontent.ai.kontent_update_itemRenames a Kontent.ai content item, changes its codename (which breaks code that refers to the old one) or moves it to another collection.kontent_set_text_elementsWrites plain text into text elements of a content item's language variant (creating the variant if the language has none)…kontent_change_workflow_stepMoves a Kontent.ai language variant to a workflow step (for example from Draft to Review); the step's assigned people may be notified by Kontent.ai.kontent_create_new_versionCreates a new draft version of a published Kontent.ai variant so it can be edited; the published version stays live until the draft is published.kontent_publishPublishes a Kontent.ai language variant, now or at scheduled_to: it goes live to every site and app reading the Delivery API…kontent_unpublishUnpublishes a Kontent.ai language variant and moves it to Archived…kontent_scheduleSets (or moves) when a Kontent.ai language variant will be published and/or unpublished…kontent_cancel_scheduled_publishCancels a Kontent.ai variant's scheduled publishing; it moves back to the first workflow step and will not go live at that time.kontent_cancel_scheduled_unpublishCancels a Kontent.ai variant's scheduled unpublishing, so it stays live.kontent_delete_variantPermanently deletes one language variant of a Kontent.ai item and its content; if it is the item's last variant the whole item is deleted.kontent_delete_itemPermanently deletes a Kontent.ai content item with ALL its language variants (published ones disappear from every site reading them).kontent_delete_assetPermanently deletes an asset that no content uses; Kontent.ai refuses one that is still referenced.
Connect it
First connect Kontent.ai on Dashboard → Connections, then add Memtro to your client once. The Kontent.ai tools appear alongside the tools of everything else you have connected; nothing is configured per connector.
Claude Code
The Memtro plugin registers the server and a skill for when to use it; the tools are then available in every session.
claude plugin marketplace add memtro-org/claude-memtro
claude plugin install memtro@memtro --config api_key=sk-memtro-...Cursor
Add the server to .cursor/mcp.json in the project, or to the global file under ~/.cursor/.
{
"mcpServers": {
"memtro": {
"url": "https://platform.memtro.com/api/mcp",
"headers": {
"Authorization": "Bearer sk-memtro-..."
}
}
}
}Claude Desktop
Create a personal API key on Dashboard → Profile → API keys. In Claude Desktop add an MCP server of type HTTP with URL https://platform.memtro.com/api/mcp and the header Authorization: Bearer sk-memtro-…
OpenCode
A remote server in opencode.json.
{
"mcp": {
"memtro": {
"type": "remote",
"url": "https://platform.memtro.com/api/mcp",
"headers": {
"Authorization": "Bearer sk-memtro-..."
}
}
}
}Pi
One command: pi mcp add memtro --url https://platform.memtro.com/api/mcp --bearer-token-env-var MEMTRO_API_KEY. Tools arrive as mcp__memtro__*. The pi-memtro extension registers it for you, alongside Memtro as the model.
Any other client
Add an MCP server of type HTTP (Streamable HTTP, stateless) at https://platform.memtro.com/api/mcp with the header Authorization: Bearer sk-memtro-.... Codex, Zed, Windsurf, Cline and the SDKs all take a remote server this way.
Who may use it
The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared Kontent.ai connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.
Ask it like this
- › Which articles are still in review?
- › What is the workflow step and schedule of the pricing page in German?
- › What elements does the blog post content type have?
- › Which languages are active in this environment?
- › Move the launch announcement to the Review step.
Questions
- Is this an official Kontent.ai MCP server?
- No. It is Memtro's MCP server with Memtro's Kontent.ai connector behind it: the connector reads Kontent.ai through its API with the credentials you connect on Dashboard → Connections, and Kontent.ai publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.
- What does it cost?
- Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.
- Can it change anything in Kontent.ai?
- Only when you ask, and only what it has been granted: create a content item; rename or recode a content item, or move it to another collection; set text elements of a draft language variant; move a language variant to a workflow step; create a new draft version of a published variant; publish a language variant now or at a set time; unpublish and archive a language variant now or at a set time; schedule publishing and unpublishing of a variant; cancel scheduled publishing; cancel scheduled unpublishing; delete a language variant; delete a content item and all its variants; delete an unused asset. Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.
- Which clients work?
- Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.