Connector guide7-minute read20 MCP tools7 languages

How to Connect Contentful to Meta Muse via MCP

Let your AI work with your Contentful content: search entries and assets, read content types, locales and tags, and create, change, publish or unpublish entries. Delivery token for reads, management token for writes.

HCBy HelpCode teamUpdated 7 min read Open-source on GitHub

No credit card · 7-day trial · Self-host alternative available

Contentful

Contentful

Let your AI work with your Contentful content: search entries and assets, read content types, locales and tags, and create, change, publish or unpublish entries. Delivery token for reads, management token for writes.

tools

20

Region

INTL

Category

CMS

Authentication

API credentials

Required env vars

CONTENTFUL_SPACE_IDCONTENTFUL_ENVIRONMENTCONTENTFUL_DELIVERY_URLCONTENTFUL_DELIVERY_TOKEN
Install in one click on Cloud

7-day free trial · No credit card

  • 7-day free trial
    No credit card required
  • GDPR & SOC 2 ready
    EU data residency, audit logs
  • Open-source on GitHub
    Open source · AGPL-3.0
  • Works with ChatGPT, Claude, Gemini
    Any MCP-compatible client

Skip the install. Get this working in under 2 minutes.

Start a free trial on cloud.anythingmcp.com, add the Contentful 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.

Start free trial

Summary

Let your AI work with your Contentful content: search entries and assets, read content types, locales and tags, and create, change, publish or unpublish entries. Delivery token for reads, management token for writes.

Try asking

Example prompts for Contentful

Click any prompt to copy it. Paste into Claude, ChatGPT, Cursor, Gemini, Copilot or OpenClaw to run it against this connector.

Contentful · live via MCP
Share
Opus 4.7

Claude is AI and can make mistakes. Please double-check responses.

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Contentful, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

Contentful + Meta Muse

Let your AI work with your Contentful content: search entries and assets, read content types, locales and tags, and create, change, publish or unpublish entries. Delivery token for reads, management token for writes.

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:

CONTENTFUL_SPACE_ID, CONTENTFUL_ENVIRONMENT, CONTENTFUL_DELIVERY_URL, CONTENTFUL_DELIVERY_TOKEN

Step 1 — Get credentials

  1. In Contentful (https://app.contentful.com), open your space, then Settings → API keys → Add API key. Name it (for example "AnythingMCP"), tick the environments it may read (at least master) and save.
  2. Copy the Space ID into CONTENTFUL_SPACE_ID and the Content Delivery API access token into CONTENTFUL_DELIVERY_TOKEN.
  3. Set CONTENTFUL_ENVIRONMENT to the environment id, usually master. Other environments are listed under Settings → Environments.
  4. Set CONTENTFUL_DELIVERY_URL to https://cdn.contentful.com, or https://cdn.eu.contentful.com for a space in the EU data region, without a trailing slash. To let the AI read drafts as well, use https://preview.contentful.com (or https://preview.eu.contentful.com) together with the Content Preview API access token of the same key.
  5. For writes, create a personal access token: avatar menu → Account settings → CMA tokens → Create personal access token. Pick an expiry and copy the token right away, as Contentful shows it only once. Paste it into CONTENTFUL_MANAGEMENT_TOKEN, without the word Bearer, and set CONTENTFUL_MANAGEMENT_URL to https://api.contentful.com (or https://api.eu.contentful.com). The token acts as you, in every space you can edit.
  6. If your organization has to approve personal access tokens, an organization admin opens Organization settings, finds the token in the access settings for personal access tokens and grants it access. Until then the write tools answer 401 OrganizationAccessGrantRequired; reads with the delivery token are not affected.
  7. Install the connector and start with contentful_get_space: it returns the space name and its locales, a quick check that the space ID and the delivery token belong together.

Two tokens, on purpose: the delivery token reads published content and nothing else (drafts too, with the preview token), so a connector set up with only the four required values can look everything up but changes nothing. Writes, unpublished drafts, spaces and environments go through the Content Management API with the personal access token. Leave CONTENTFUL_MANAGEMENT_URL and CONTENTFUL_MANAGEMENT_TOKEN empty and the management tools simply report that they are missing.

Publishing changes your live site: contentful_publish_entry and contentful_unpublish_entry change what visitors see on your website or app, so the AI names the entry and the effect and waits for your yes. contentful_delete_entry is switched off at install, as a deleted entry cannot be restored.

How edits work: contentful_list_content_types gives the content type and field ids, contentful_list_locales the locale codes. Field values are keyed by field id and then by locale, for example {"title": {"en-US": "Hello"}}. Before each change the AI reads the entry with contentful_get_entry_for_editing to get its current sys.version; if someone else saved in between, Contentful answers 409 VersionMismatch and the AI reads again. contentful_update_entry replaces all fields, so anything left out is deleted; for one or two fields the AI uses contentful_patch_entry. A change goes live only when the new version is published.

Searching: contentful_list_entries takes a content_type, a full-text query and further filters such as fields.slug=hello or fields.date[gte]=2026-01-01. Filtering or sorting by a field needs content_type. Linked entries and assets come back in includes, and asset URLs start with //, so the AI adds https:.

Paging: lists return total, skip and limit (up to 1,000); the next page starts at skip + limit.

Common errors: 401 AccessTokenInvalid means a wrong or expired token, or a delivery token used on the preview host (or the other way round). 404 NotFound is a wrong id, or a space or environment the token does not cover: Contentful answers 404 here, not 403. 400 "A Content Type ID is required" means a field filter without content_type. 422 ValidationFailed names the field that is empty or breaks a validation. 429 RateLimitExceeded: the management API allows about 7 requests a second, so wait and retry.

The connector does not upload assets, create or edit content types, or manage environments, webhooks, roles and apps, and it does not use the GraphQL API.

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 Muse

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 shows YOUR_SERVER_ID.

Muse adds remote MCP servers as custom connectors and signs in to them with OAuth.

  1. In Muse, open Settings → Connectors and choose Add custom connector.
  2. Paste the MCP server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID.
  3. Muse opens the AnythingMCP sign-in page: sign in and approve access.
  4. In a chat, ask Muse for something that needs the Contentful tools.

You can also set it up from a chat, on the web, in the iOS and Android apps or in WhatsApp. Send Muse this message:

Create a Custom Connector for a new remote MCP server, then connect to it:
Name: AnythingMCP
Transport: remote streamable HTTP
URL: https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID
Auth: OAuth

Self-hosting? Use your instance's public HTTPS address instead of https://cloud.anythingmcp.com. Muse connects from Meta's cloud, so localhost does not work.

Available tools

ToolWhat it does
contentful_get_spaceRead the space the connector is set up for (Content Delivery API): its name and locales with the default locale
contentful_list_content_typesList the content types of the environment (Content Delivery API): for each its sys.id (the id entries are filtered by), name, displayField…
contentful_get_content_typeRead one content type by id (Content Delivery API): its fields with id, name, type (Symbol, Text, RichText, Integer, Number, Date, Boolean…
contentful_list_entriesSearch published entries (Content Delivery API)
contentful_get_entryRead one published entry by id (Content Delivery API): sys (id, contentType, createdAt, updatedAt, revision), metadata.tags and fields
contentful_list_assetsSearch published assets (images, documents, videos) via the Content Delivery API
contentful_get_assetRead one published asset by id (Content Delivery API): title, description and file with url (prefix https:), fileName, contentType, size…
contentful_list_localesList the locales of the environment (Content Delivery API): code (e.g. en-US, de-DE), name, default flag and fallbackCode
contentful_list_tagsList the public content tags of the environment (Content Delivery API) with sys.id and name
contentful_list_spacesList the spaces the management token can reach (Content Management API), with sys.id and name
contentful_list_environmentsList the environments of the space (Content Management API), e.g. master, staging, with sys.id, name, status and aliases
contentful_list_all_entriesSearch all entries including drafts and changed-but-unpublished versions (Content Management API)
contentful_get_entry_for_editingRead the latest version of an entry, draft changes included (Content Management API): fields with every locale, metadata.tags and…
contentful_create_entryCreate a draft entry of a content type (Content Management API). fields maps each field id to its values per locale, e.g. {"title"…
contentful_update_entryReplace the fields of an entry (Content Management API)
contentful_patch_entryChange single fields of an entry with JSON Patch operations (Content Management API), leaving the rest untouched
contentful_publish_entryPublish an entry, making its current version visible on the website or app through the delivery API (Content Management API). version must…
contentful_unpublish_entryUnpublish an entry: it disappears from the delivery API, so from the website or app, and stays as a draft (Content Management API)
contentful_delete_entryDelete an entry for good (Content Management API)
contentful_create_tagCreate a content tag in the environment (Content Management API)

Example prompts

  • "Find the blog posts we published in the last 30 days and list each one's title, slug and author."
  • "Which entries have saved changes that are not published yet?"
  • "List the images we uploaded this month, with their file size and dimensions."
  • "Change the headline of the spring sale landing page to 'Spring sale: 20% off everything' and publish it once I confirm."

FAQ

Where is Muse available? Meta currently offers Muse in the US and Canada, on the web, in the iOS and Android apps and in WhatsApp.

Does Meta review this connector? No. Meta doesn't review custom connectors. Muse sees only the tools you switched on for this MCP server in AnythingMCP, and you can disconnect it anytime under Settings → Connectors.

Next steps

Was this guide helpful?

Your Contentful agent is one click away.

Install the connector, paste the key, prompt Meta Muse. Free for 7 days, no credit card.

Related guides

Connectors

How to Connect Contentful to ChatGPT via MCP

Let your AI work with your Contentful content: search entries and assets, read content types, locales and tags, and create, change, publish or unpublish entries. Delivery token for reads, management token for writes.

Connectors

How to Connect Contentful to Claude via MCP

Let your AI work with your Contentful content: search entries and assets, read content types, locales and tags, and create, change, publish or unpublish entries. Delivery token for reads, management token for writes.

Connectors

How to Connect Contentful to Cursor via MCP

Let your AI work with your Contentful content: search entries and assets, read content types, locales and tags, and create, change, publish or unpublish entries. Delivery token for reads, management token for writes.

Connectors

How to Connect Contentful to Gemini via MCP

Let your AI work with your Contentful content: search entries and assets, read content types, locales and tags, and create, change, publish or unpublish entries. Delivery token for reads, management token for writes.

Connectors

Contentful to MCP: Drive Contentful from any AI Agent

Let your AI work with your Contentful content: search entries and assets, read content types, locales and tags, and create, change, publish or unpublish entries. Delivery token for reads, management token for writes.

Connectors

How to Connect Canva to Meta Muse via MCP

Let your AI work in Canva: find and read designs, create new ones, export them to PDF, PNG, PowerPoint or video with download links, organise folders, upload images from a link, read brand templates and comment on designs.