An MCP (Model Context Protocol) server that connects AI agents like Cursor and Claude Code to your NomaCMS project. Manage collections, fields, content entries, assets, and webhooks programmatically through natural language.
NOMA_API_KEY: API key from User settings → API keys — see API key abilities.
NOMA_PROJECT_ID: Your project's UUID — you can find it on the project home page or under Project settings → API Access
Related MCP server: elmapicms-mcp-server
Add this to your Cursor MCP settings (~/.cursor/mcp.json):
{
"mcpServers": {
"nomacms": {
"command": "npx",
"args": ["-y", "@nomacms/mcp-server"],
"env": {
"NOMA_API_KEY": "your-api-key",
"NOMA_PROJECT_ID": "your-project-uuid"
}
}
}
}Add the MCP server using the Claude Code CLI:
claude mcp add nomacms \
-e NOMA_API_KEY=your-api-key \
-e NOMA_PROJECT_ID=your-project-uuid \
-- npx -y @nomacms/mcp-serverget_project — Get project information (default_locale, locales, etc.)
add_project_locale — Add a locale code to the project (requires admin)
set_default_project_locale — Set the default locale (requires admin)
Removing locales is intentionally not exposed here (use Project settings → Localization in the NomaCMS dashboard if you must remove a locale).
list_collections — List all collections
get_collection — Get a collection with its full field schema
create_collection — Create a collection (with optional batch field creation)
update_collection — Update a collection's name and slug
reorder_collections — Reorder collections
create_field — Add a field to a collection
update_field — Update a field
reorder_fields — Reorder fields within a collection
list_entries — List entries with advanced filtering (where with 13 operators, OR groups, relation filtering), sorting, pagination, count, and first
get_entry — Get a single content entry
create_entry — Create a content entry
update_entry — Update a content entry
patch_entry — Partially update an entry (HTTP PATCH; merge only the fields you send)
publish_entry — Publish the draft as a new immutable version (update)
unpublish_entry — Clear the live published pointer; versions retained (update)
delete_entry — Soft-delete a content entry (moves to trash)
bulk_create_entries — Create multiple entries atomically
bulk_update_entries — Update multiple entries atomically by UUID
bulk_delete_entries — Delete multiple entries atomically by UUID
link_entry_translation — Link two entries (different locales) into the same translation group (POST …/link-translation; requires update ability)
list_entry_versions — List version history for an entry
get_entry_version — Fetch one version by number (includes snapshot payload)
revert_entry_version — Restore draft from a prior snapshot and publish (update)
update_entry_version_label — Edit label/description on a version; snapshot unchanged (update)
Content API shape: Each entry has uuid, locale, published_at, and fields (custom field values). Richtext values are markdown strings on write; on read they are either raw markdown or rendered HTML depending on the field’s editor.outputFormat (markdown vs html). Relation fields return nested entry objects (or arrays for one-to-many) on read; on write send only the related entry’s UUID or numeric id (never the full nested object from a previous get_entry). get_entry supports translation_locale, exclude, timestamps, and state query parameters.
Asset URLs: The API returns url, thumbnail_url, and original_url as stable links (optional ?variant=thumbnail or ?variant=original).
list_assets — List assets with pagination
get_asset — Get an asset by UUID or filename
upload_asset — Upload a file as an asset
bulk_upload_assets — Upload multiple files atomically
bulk_update_asset_metadata — Update metadata for multiple assets atomically
delete_asset — Delete an asset
list_webhooks — List all webhooks for the project
get_webhook — Get a webhook by UUID
create_webhook — Create a webhook for content and auth events (name, url, events, sources; optional description, secret, payload, status, collection_ids)
update_webhook — Update a webhook by UUID (same fields as create)
delete_webhook — Delete a webhook by UUID
list_webhook_logs — List delivery logs for a webhook (uuid; optional paginate, page)
The server exposes three reference resources that AI agents can read for context:
Field Types Reference (nomacms://field-types) — Complete reference of all 16 field types, their options, validations, and common patterns.
Collections Guide (nomacms://collections-guide) — Guide for working with collections, singletons, reserved slugs, and best practices.
Query Reference (nomacms://query-reference) — Full documentation for content queries: where filters with 13 operators, OR groups, relation filtering, sorting, pagination, and examples.
Your API key needs the appropriate abilities for the tools you want to use:
Ability | Tools |
| list/get collections, entries, assets, webhooks; webhook logs |
| create entries, upload assets, create webhooks |
| update entries, |
| delete entries, delete assets, delete webhooks |
| create/update/reorder collections and fields; add/set default project locales (MCP does not expose locale removal) |
Create the key in the NomaCMS dashboard under User settings → API keys. Copy the Project ID from the project home page or Project settings → API Access when you configure this server.
Each MCP entry connects to a single NomaCMS project. To work with multiple projects, add separate entries in your MCP config:
{
"mcpServers": {
"nomacms-blog": {
"command": "npx",
"args": ["-y", "@nomacms/mcp-server"],
"env": {
"NOMA_API_KEY": "blog-project-api-key",
"NOMA_PROJECT_ID": "blog-project-uuid"
}
},
"nomacms-store": {
"command": "npx",
"args": ["-y", "@nomacms/mcp-server"],
"env": {
"NOMA_API_KEY": "store-project-api-key",
"NOMA_PROJECT_ID": "store-project-uuid"
}
}
}
}MIT
Add a locale code (e.g. tr, es) to the project. Requires admin API ability. Codes are lowercased. Call when setting up a multilingual site before creating translated content.
Inputs: locale (required).
Create multiple content entries atomically. If one item fails, the whole request is rolled back.
Inputs: items (required), collection_slug (required).
Delete multiple content entries atomically by UUID. If one delete fails, no entries are deleted.
Inputs: uuids (required), collection_slug (required), force.
Update metadata for multiple assets atomically by UUID. If one item fails, all updates are rolled back.
Inputs: items (required).
Update multiple content entries atomically by UUID. If one item fails, all updates are rolled back. Saves never change publish state — call publish_entry per UUID to mint new versions after bulk updates.
Inputs: items (required), collection_slug (required).
Upload multiple local files as assets atomically. If one upload fails, all uploads are rolled back.
Inputs: file_paths (required).
Create a new collection. Optionally include field definitions to create the collection with its full schema in a single request.
Inputs: name (required), slug (required), fields, is_singleton.
Create a new content entry in a collection
Inputs: data (required), collection_slug (required), state, locale, +1 more.
Add a new field to a collection
Inputs: name (required), type (required), label (required), collection_slug (required), +5 more.
Create a webhook for content and auth events
Inputs: url (required), name (required), events (required), sources (required), +5 more.
Delete an asset by UUID
Inputs: uuid (required).
Soft-delete a content entry (moves to trash). Can be restored from the admin panel.
Inputs: uuid (required), collection_slug (required).
Delete a webhook by UUID
Inputs: uuid (required).
Get an asset by its UUID or by filename.
Inputs: identifier (required), by_name.
Get a single collection with its full field schema by slug
Inputs: slug (required).
Get a single content entry by UUID. Response includes uuid, locale, published_at, and a fields object (custom field values — not a nested data key). Relation fields appear as nested entry objects (one-to-one) or arrays of entries (one-to-many), not as bare UUIDs.
Inputs: uuid (required), collection_slug (required), state, locale, +3 more.
Fetch a single version's metadata and raw snapshot payload. The snapshot contains the saved field values in restoration format; for API-rendered content use get_entry with state='published'.
Inputs: uuid (required), version_number (required), collection_slug (required).
Get information about the current Noma project (name, uuid, default_locale, locales, etc.)
Inputs: no named parameters.
Get a webhook by UUID
Inputs: uuid (required).
Merge two entries in the same collection into one translation group (same as dashboard “link translation”). Both entries must exist, belong to this collection, and have different locales. There is no unlink via API — use the dashboard if you need to split a group. Requires an API key with update ability.
Inputs: uuid (required), collection_slug (required), translation_entry_uuid (required).
List assets in the project with optional pagination.
Inputs: page, paginate, per_page.
List all collections in the project
Inputs: no named parameters.
List content entries for a collection with advanced filtering, sorting, and pagination. Use the 'where' parameter for powerful queries. Read the 'query-reference' resource for full documentation on operators and examples.
Inputs: collection_slug (required), sort, count, first, +7 more.
List all published versions for a content entry (newest first). Each version is an immutable snapshot taken at publish time. Response includes version_number, label, description, published_at, created_by, and is_current_published for each version.
Inputs: uuid (required), collection_slug (required).
List delivery logs for a webhook
Inputs: uuid (required), page, paginate.
List all webhooks configured for the current project
Inputs: no named parameters.
Partially update a content entry (HTTP PATCH). Only include fields you want to change (e.g. relations, one field). Saves NEVER change the publish state — call publish_entry explicitly to mint a new version. Prefer this over update_entry when you are not replacing the entire entry.
Inputs: data (required), uuid (required), collection_slug (required), locale.
Mint a new immutable version from the entry's current draft and make it the live published version. After this call, state=published reads from the public API will return the new snapshot and is_draft_dirty is reset to false.
Inputs: uuid (required), collection_slug (required).
Update the display order of collections
Inputs: collections (required).
Update the display order of fields within a collection
Inputs: fields (required), collection_slug (required).
Restore the draft to a previous version's snapshot and publish it as a new version. The current unpublished draft is replaced. Returns the new version number.
Inputs: uuid (required), version_number (required), collection_slug (required).
Set the project's default locale. Adds the locale to the list if it was missing. Requires admin API ability.
Inputs: locale (required).
Clear the live published pointer for an entry. The entry becomes invisible under state=published in the public API, but all historical versions are retained and still accessible via list_entry_versions / get_entry_version.
Inputs: uuid (required), collection_slug (required).
Update the name and slug of an existing collection
Inputs: name (required), slug (required), new_slug (required).
Replace an existing content entry (HTTP PUT). Sends the full data payload; required fields (e.g. title, slug) must be included. Saves NEVER change the publish state — if the entry has a published version, the public API keeps serving that snapshot under state=published until you explicitly call publish_entry. Use patch_entry for partial updates and publish_entry/unpublish_entry to control visibility.
Inputs: data (required), uuid (required), collection_slug (required), locale.
Update a version's editable label and/or description. The snapshot payload itself is immutable.
Inputs: uuid (required), version_number (required), collection_slug (required), label, +1 more.
Update an existing field on a collection
Inputs: name (required), type (required), label (required), field_uuid (required), +5 more.
Update a webhook by UUID
Inputs: url (required), name (required), uuid (required), events (required), +6 more.
Upload a local file as an asset. Provide the absolute file path.
Inputs: file_path (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 39 tools
Each tool targets a distinct operation or resource. Bulk and single operations are clearly separated, and actions like publish, unpublish, patch, and update are well-differentiated through descriptions.
The naming follows a consistent verb_noun pattern in snake_case, with minor exceptions like 'link_entry_translation' and 'reorder_collections' that break the pattern slightly.
At 39 tools, the server is overpopulated for a typical CMS MCP server. While the domain is broad, many tools could be consolidated (e.g., bulk operations as parameters).
The tool surface covers most CRUD operations for entries, assets, collections, fields, and webhooks, but lacks delete operations for collections and fields, and asset file update is missing.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
