# Contentful MCP connector

The Contentful connector brings entries, assets, content types, releases and locales into Elaichi, so Claude, ChatGPT, Cursor and the Elaichi Agent can read and update your spaces as each signed-in person, with every change logged.

Source: https://elaichi.ai/connectors/contentful/

## Facts

| | |
| --- | --- |
| Application | Contentful |
| Category | Application Development |
| Authentication | Connects over OAuth |
| Bring your own OAuth app | No |
| Native MCP | Yes. Contentful builds and runs this MCP server. Elaichi adds sign-in, access controls and an audit log on top |
| Support for its tools | www.contentful.com/help/getting-started/how-to-get-help |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once Contentful is connected

- Which entries in the marketing space are still in draft?
- List assets uploaded this week that have no alt text.
- What is in the spring launch release and is it ready?

## Connect Contentful in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick Contentful.
2. Optionally set Share with, then press Connect.
3. Approve it in Contentful. Contentful's own window opens. Whoever approves it decides what this connection can reach.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Contentful tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Contentful MCP connector for Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## Contentful MCP connector for ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web today. The plugin directory lives at chatgpt.com/plugins.

## Contentful MCP connector for Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## Connect Contentful to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Only Read is granted by default, which is not enough to call a Contentful tool. Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Grant Read and Run tools. Think hard before granting Delete, which reaches into connected apps and cannot be undone.

## What teams do with Contentful through Elaichi

### Draft the landing page entry before launch

Marketing. Ask for a new landing page entry in the marketing space with the headline, hero asset and call to action already filled in. Review it in Contentful and publish when the campaign is ready.

### Find every entry that mentions old pricing

Content. Ask which entries across your spaces still reference last year's plan names, then have each one updated with the new wording. Nothing goes live until an editor publishes it.

### See which locales are still missing translations

Localization. Ask which entries have a German or Japanese field left empty before a regional launch. Send the list to translators or draft the missing fields for review.

### Check what is in the next release

Product. Ask what entries sit inside the release scheduled for Thursday and whether any are still in draft. Add the late release notes entry without opening the release yourself.

### Update a help article after a policy change

Documentation. Ask for every help center entry that describes the refund process, then have the changed paragraph rewritten in each one. Each edit appears in Contentful as a draft under your name.

### Confirm a content type before changing a field

Engineering. Ask which content types use a given field and how many entries would be affected in the staging environment. Add the new field once the answer is clear.

## Elaichi vs Zapier MCP vs Composio for Contentful

All three can connect Contentful to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

| What to check | Elaichi | Zapier MCP | Composio |
| --- | --- | --- | --- |
| Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Contentful tools | Allow or restrict single Contentful tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Contentful call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | $15 per user per month. | 2 tasks per successful call. | Billed per tool call. |

Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## Frequently asked questions

### How do I connect Contentful to Claude?

Open Elaichi, choose Contentful and sign in to Contentful with your own account to authorize it over OAuth. There is no OAuth application to register and no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Your Contentful spaces are available in Claude from that point.

### Does Contentful work with ChatGPT and Cursor as well as Claude?

Yes. Once Contentful is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client and the Elaichi Agent. You connect Contentful once and every client picks it up.

### What can an AI agent actually do with my Contentful content?

An agent connected to Contentful through Elaichi can read and write entries, assets, content types, releases and locales across your spaces and environments. In practice that means finding entries still in draft, filling a missing locale field, adding an entry to a release or updating a help article after a policy change. Short, concrete asks such as "list draft entries in the marketing space" work better than long sentences.

### Does connecting Contentful give the AI access to every space and environment?

No. Access to Contentful follows the person who signed in, so an agent can only reach the spaces, environments and locales that person can already open in Contentful. Elaichi can narrow that further for a team or a toolbox, but it can never widen it beyond what Contentful itself allows.

### Can my team share one Contentful connection?

Yes. One person connects Contentful in Elaichi and shares the connection with a team, and nobody else ever handles a token or credential. Each teammate still signs in to Elaichi as themselves, so every entry edit or asset upload in the audit log carries their own name.

### Can I stop an agent from deleting or changing things in Contentful?

Yes. Restrictions in Elaichi apply per action, so you can allow reading Contentful entries while blocking publishing, unpublishing or deleting. A restricted action is never advertised to the AI client at all, so no prompt, however worded, can reach it.

### What happens to a Contentful connection when someone leaves?

Offboarding that person in Elaichi ends their access to Contentful through every client at once. If they had shared a Contentful connection with a team, it keeps working for everyone else. Disconnecting Contentful once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client together.

### Does the Contentful MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Contentful is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

### Is Elaichi an alternative to Zapier MCP for Contentful?

Yes. Both let Claude, ChatGPT or Cursor use Contentful. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Contentful call.

### How is Elaichi different from Composio for Contentful?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Contentful: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.