Merge Unified's Contentful integration Merge Agent Handler's Contentful MCP server

Connect your AI Agents to Contentful in minutes

Merge lets you securely connect your agents to Contentful and thousands of tools instantly

Start building for free

Read docs

Contentful

Learn more about Merge Agent Handler

Available tools

list_assets

List assets in a Contentful environment. Optionally filter by MIME type group.

get_asset

Get a Contentful asset by ID.

create_asset

Create a new asset in Contentful. Must be processed and published after creation.

update_asset

Update a Contentful asset. Requires current version for optimistic locking.

delete_asset

Delete a Contentful asset. Must be unpublished first.

publish_asset

Publish a Contentful asset to make it available via the Content Delivery API.

unpublish_asset

Unpublish a Contentful asset to remove it from the Content Delivery API.

process_asset

Process a Contentful asset for a specific locale. Downloads and stores the file.

list_content_types

List all content types in a Contentful environment.

get_content_type

Get a Contentful content type by ID.

create_content_type

Create a new content type in Contentful. Must be published before entries can be created.

update_content_type

Update a Contentful content type. Requires current version for optimistic locking.

delete_content_type

Delete a Contentful content type. Must be unpublished first and have no entries.

publish_content_type

Publish a Contentful content type. Required before entries can be created.

unpublish_content_type

Unpublish a Contentful content type. All entries must be deleted first.

list_entries

List entries in a Contentful environment. Filter by content type or query parameters.

get_entry

Get a Contentful entry by ID.

create_entry

Create a new entry in Contentful. Specify content type and field values by locale.

update_entry

Update a Contentful entry. Requires current version for optimistic locking.

delete_entry

Delete a Contentful entry. Must be unpublished first.

publish_entry

Publish a Contentful entry to make it available via the Content Delivery API.

unpublish_entry

Unpublish a Contentful entry to remove it from the Content Delivery API.

archive_entry

Archive a Contentful entry. Must be unpublished first.

unarchive_entry

Unarchive a Contentful entry to make it editable again.

list_environments

List all environments in a Contentful space.

get_environment

Get a Contentful environment by ID.

create_environment

Create a new Contentful environment. Optionally clone from an existing environment.

delete_environment

Delete a Contentful environment. WARNING: Cannot delete the master environment.

list_locales

List all locales in a Contentful environment.

get_locale

Get a Contentful locale by ID.

create_locale

Create a new locale in a Contentful environment.

update_locale

Update a Contentful locale. Requires current version for optimistic locking.

delete_locale

Delete a Contentful locale. Cannot delete the default locale.

list_spaces

List all Contentful spaces accessible to the authenticated user.

get_space

Get a Contentful space by ID.

create_space

Create a new Contentful space. Requires organization_id for paid accounts.

update_space

Update a Contentful space name. Requires current version for optimistic locking.

delete_space

Delete a Contentful space. WARNING: This permanently deletes the space and all its content.

validate_credential

Validate Contentful credentials. Verifies credentials during setup.

list_webhooks

List all webhooks in a Contentful space.

get_webhook

Get a Contentful webhook by ID.

create_webhook

Create a new webhook in a Contentful space to receive notifications for content events.

update_webhook

Update a Contentful webhook. Requires current version for optimistic locking.

delete_webhook

Delete a Contentful webhook.

get_webhook_calls

Get recent call details for a Contentful webhook.

get_webhook_health

Get health status for a Contentful webhook.

View all tools by creating a free account See more tools

How to set up Merge Agent Handler

In an mcp.json file, add the configuration below, and restart Cursor.

Learn more in the official documentation ↗

1{
2  "mcpServers": {
3    "agent-handler": {
4      "url": "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
5      "headers": {
6        "Authorization": "Bearer yMt*****"
7      }
8    }
9  }
10}
11

Copy Code

Open your Claude Desktop configuration file and add the server configuration below. You'll also need to restart the application for the changes to take effect.

Make sure Claude is using the Node v20+.

Learn more in the official documentation ↗

1{
2  "mcpServers": {
3    "agent-handler": {
4      "command": "npx",
5      "args": [
6        "-y",
7        "mcp-remote@latest",
8        "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
9        "--header",
10        "Authorization: Bearer ${AUTH_TOKEN}"
11      ],
12      "env": {
13        "AUTH_TOKEN": "yMt*****"
14      }
15    }
16  }
17}

Copy Code

Open your Windsurf MCP configuration file and add the server configuration below.
Click on the refresh button in the top right of the Manage MCP server page or in the top right of the chat box in the box icon.

Learn more in the official documentation ↗

1{
2    "mcpServers": {
3      "agent-handler": {
4        "command": "npx",
5        "args": [
6          "-y",
7          "mcp-remote@latest",
8          "https://ah-api.merge.dev/api/v1/tool-packs/<tool-pack-id>/registered-users/<registered-user-id>/mcp",
9          "--header",
10          "Authorization: Bearer ${AUTH_TOKEN}"
11        ],
12        "env": {
13          "AUTH_TOKEN": "<ah-production-access-key>"
14        }
15      }
16    }
17  }

Copy Code

In Command Palette (Cmd+Shift+P on macOS, Ctrl+Shift+P on Windows), run "MCP: Open User Configuration".

You can then add the configuration below and press "start" right under servers. Enter the auth token when prompted.

Learn more in the official documentation ↗

1{
2  "inputs": [
3    {
4      "type": "promptString",
5      "id": "agent-handler-auth",
6      "description": "Agent Handler AUTH_TOKEN", // "yMt*****" when prompt
7      "password": true
8    }
9  ],
10  "servers": {
11    "agent-handler": {
12      "type": "stdio",
13      "command": "npx",
14      "args": [
15        "-y",
16        "mcp-remote@latest",
17        "https://ah-api-develop.merge.dev/api/v1/tool-packs/{TOOL_PACK_ID}/registered-users/{REGISTERED_USER_ID}/mcp",
18        "--header",
19        "Authorization: Bearer ${input:agent-handler-auth}"
20      ]
21    }
22  }
23}

Copy Code

FAQs on using Merge's Contentful MCP server

What is a Contentful MCP server?

It’s an MCP server that exposes functionality and tools from Contentful via tools. Your agents can use these tools to create new assets, unpublish assets, share links to assets in Slack, and more.

How can I use the Contentful MCP server?

Here are some use cases:

Connect an agent to Contentful content without building custom API glue. Let your agent browse Contentful spaces and entries, then pull the exact content it needs for a response or workflow

Draft and update content from natural language. Create or update entries (for example, landing page copy, FAQs, changelog posts) based on a prompt, then write them into Contentful as a new draft

Create content ops workflows. Triage a list of requested edits, apply changes across many entries, and keep fields consistent (titles, slugs, metadata, references)

Implement content quality and governance measures. Find missing fields, inconsistent metadata, or outdated content, then propose fixes (or apply them) across your content model

Add localization support: Duplicate an entry into multiple locales, populate translated fields, and flag what is still missing before publishing

Coordinate releases and publishing. Prep a batch of entries for a release, move items through draft to ready for review, and (if your server supports it) publish at the right time

What makes Merge Agent Handler’s Contentful MCP server better than alternative Contentful MCP servers?

Merge Agent Handler provides platform-level capabilities that extend beyond what you can do with Contentful’s official MCP server. This includes:

Enterprise-grade security and DLP: All tool inputs and outputs pass through a security gateway that can block, redact, or mask sensitive data using default or custom rules. This helps prevent data leakage during agent-initiated Contentful actions

Real-time observability and audit trails: Every tool call is logged with full request and response metadata. Logs are fully searchable, making it easier to audit agent behavior, debug failures, and optimize workflows over time

Managed authentication and credential handling: Merge Agent Handler handles connector authentication flows, including user onboarding and credential storage, so agents can invoke tools without embedding secrets or custom auth logic

Evaluation Suite: Pressure-test your Contentful tool calls before production with an evaluation suite to validate that the connector behaves consistently across prompts and scenarios

Can I set custom security rules for Contentful tool calls in Merge Agent Handler?

Yes. Merge Agent Handler allows you to configure custom security and data-loss-prevention (DLP) rules that inspect Contentful tool inputs and outputs. Rules can block, redact, or mask sensitive fields based on your organization’s policies.

Here some specific examples:

Prevent publishing secrets into Contentful. Block any <code class="blog_inline-code">create_entry</code> or <code class="blog_inline-code">update_entry</code> tool call if the payload includes API keys, bearer tokens, passwords, or other credential-like strings

Stop PII from being stored in CMS fields. Block tool calls that attempt to write SSNs, credit card numbers, or other sensitive entities into Contentful fields (for example, bio fields)

Redact sensitive values while still allowing the action. Allow the tool call to execute, but automatically redact flagged entities in the underlying API request behind the tool call

Mask sensitive data on reads before it reaches the agent. When your agent reads entries, mask internal identifiers or other sensitive tokens so the agent can’t copy/paste them into other systems

Use custom regex-based rules for your org’s patterns. Add regex rules for things like proprietary customer IDs, internal environment URLs, or “do-not-publish” markers that appear in drafts