How is this different from connecting Contentful MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the Contentful MCP API changes?

We track the Contentful MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different Contentful tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in Contentful?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the Contentful MCP server myself?

No. TrustGate connects to the Contentful MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to Contentful directly.

Connect Contentful MCP to your AI agents, securely.

Q: Is Contentful MCP secure?

The server itself exposes 82 tools, and some of them can write to your Contentful account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches Contentful.

One secured endpoint for every Contentful call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try Contentful MCP now

What your agents can ask once Contentful MCP is connected.

Select the tools your AI agents can call

82 tools from the Contentful MCP schema.

Showing 82 tools

get_initial_contextreadInitializes the connection and returns usage instructions, including the default space and environment.
search_entriesreadSearches content entries with query filters.
semantic_searchreadSearches entries semantically rather than by exact field match.
get_entryreadGets a single entry with its fields.
get_entry_snapshotreadGets a version snapshot of an entry.
resolve_entry_referencesreadResolves the references an entry links to.
create_entrywriteCreates a content entry.
update_entrywriteUpdates the fields of an entry.
publish_entrywritePublishes an entry, making it live on the delivery API.
unpublish_entrywriteUnpublishes an entry, removing it from the delivery API.
archive_entrywriteArchives an entry.
unarchive_entrywriteRestores an archived entry.
delete_entryhigh riskDeletes an entry permanently.
list_content_typesreadLists the content types in an environment.
get_content_typereadGets a content type with its field definitions.
create_content_typewriteCreates a content type.
update_content_typewriteUpdates a content type's definition.
publish_content_typewritePublishes a content type so entries can use it.
unpublish_content_typewriteUnpublishes a content type.
disable_content_type_fieldwriteDisables a field on a content type.
omit_content_type_fieldwriteOmits a field from the delivery API response.
delete_content_typehigh riskDeletes a content type. Entries of that type can no longer be used.
delete_content_type_fieldhigh riskDeletes a field from a content type, discarding the data stored in it across every entry.
list_assetsreadLists the media assets in an environment.
get_assetreadGets an asset with its file metadata.
create_upload_sessionwriteCreates a short-lived upload session. The returned handle is a single-use capability token valid for one hour.
upload_assetwriteCreates an asset from staged bytes referenced by an upload handle.
update_assetwriteUpdates an asset's metadata.
publish_assetwritePublishes an asset to the delivery API.
unpublish_assetwriteUnpublishes an asset.
archive_assetwriteArchives an asset.
unarchive_assetwriteRestores an archived asset.
delete_assethigh riskDeletes an asset permanently.
list_releasesreadLists the releases in an environment.
get_releasereadGets a release and the entries and assets it holds.
validate_releasereadValidates a release before it is published.
get_release_actionreadGets the status of a release action.
list_release_actionsreadLists the actions queued against releases.
list_scheduled_actionsreadLists the scheduled publish and unpublish actions.
create_releasewriteCreates a release grouping entries and assets.
update_releasewriteUpdates the contents of a release.
unpublish_releasewriteUnpublishes the items in a release together.
schedule_publish_releasewriteSchedules a release to publish at a future time.
schedule_unpublish_releasewriteSchedules a release to unpublish at a future time.
cancel_scheduled_releasewriteCancels a scheduled release action.
publish_releasehigh riskPublishes every entry and asset in a release at once, live on the delivery API.
list_spacesreadLists the spaces the identity can access.
get_spacereadGets the details of a space.
list_environmentsreadLists the environments in a space.
create_environmentwriteCreates an environment in a space.
delete_environmenthigh riskDeletes an environment and everything in it.
list_orgsreadLists the organizations the identity can access.
get_orgreadGets the details of an organization.
list_localesreadLists the locales configured in an environment.
get_localereadGets the details of a locale.
create_localewriteAdds a locale for multi-language content.
update_localewriteUpdates a locale's settings.
delete_localewriteRemoves a locale from the environment.
list_tagsreadLists the tags used to organize content.
create_tagwriteCreates a tag.
list_ai_actionsreadLists the AI Actions defined in the environment.
get_ai_actionreadGets the definition of an AI Action.
get_ai_action_invocationreadGets the result of a previous AI Action invocation.
create_ai_actionwriteCreates an AI Action.
update_ai_actionwriteUpdates an AI Action's definition.
publish_ai_actionwritePublishes an AI Action so it can be invoked.
unpublish_ai_actionwriteUnpublishes an AI Action.
delete_ai_actionwriteDeletes an AI Action.
invoke_ai_actionhigh riskInvokes an AI Action, running an AI-powered workflow with its own side effects and cost.
list_conceptsreadLists the concepts in the taxonomy.
get_conceptreadGets a concept and its relationships.
list_concept_schemesreadLists the concept schemes.
get_concept_schemereadGets a concept scheme and the concepts in it.
create_conceptwriteCreates a concept.
update_conceptwriteUpdates a concept.
delete_conceptwriteDeletes a concept from the taxonomy.
create_concept_schemewriteCreates a concept scheme.
update_concept_schemewriteUpdates a concept scheme.
delete_concept_schemewriteDeletes a concept scheme.
list_editor_interfacesreadLists the editor interfaces in an environment.
get_editor_interfacereadGets how the fields of a content type appear in the entry editor.
update_editor_interfacewriteConfigures how fields appear in the entry editor.

What Contentful MCP exposes

Contentful MCP groups its 82 tools into 12 categories, each with a suggested starting policy.

All 82 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Context & Setup	Initializing the connection and returning usage instructions	Read	Call this first; it carries the space and environment defaults
Entries	Content entries end to end, including semantic search, archiving, version snapshots and reference resolution	Read / Write	Start read-only in the MCP app, then enable writes; approve deletes and publishes
Content Types	Inspecting and evolving the content model, including field-level changes	Read / Write	Model changes affect every entry of that type; require approval
Assets	Uploading, organizing, archiving and publishing media assets	Read / Write	Upload handles are capability tokens; treat them like secrets
Releases	Grouping entries and assets into a release, then validating, publishing or unpublishing them together, immediately or on a schedule	Read / Write	Validate before publishing; a release ships many items at once
Spaces & Environments	Discovering and managing spaces and environments	Read / Write	Environment aliases are not supported; reference the underlying environment ID
Organizations	The organizations the identity can access	Read	Allow read-only discovery
Locales	Locales for multi-language content	Read / Write	Removing a locale affects localized content everywhere
Tags	Tags for organizing content	Read / Write	Low risk; allow broadly
AI Actions	Creating and invoking AI-powered workflows with Contentful AI Actions	Read / Write	Invoking an action runs a workflow with its own side effects and cost
Taxonomy	Concepts and concept schemes in the taxonomy system	Read / Write	Taxonomy changes reshape how content is classified
Editor Interfaces	How fields appear in the entry editor	Read / Write	Changes affect what every editor sees

Connect Contentful MCP to your AI agent

Four steps, under ten minutes.

01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
03
Connect Contentful
Find Contentful in the tool list and connect it.
04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.

Permissions down to the single tool

You do not allow Contentful MCP or block it. You allow the exact tools each agent can call, one by one.

Contentful MCP	82 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 82 tools

Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
Default denyA tool you have not enabled is never exposed to the agent.
Approval on writesTools that change or delete things can require a human to confirm.

Is Contentful MCP secure?

One endpoint instead of raw credentials. Every call is checked against policy and logged.

AI agentsConnect through your MCP client configuration.	NeuralTrustApply controls based on your configuration.	Contentful MCP82 documented tools.
Coding assistants	Connection & credentialsper user	Releases13 tools
Internal copilots	Tool access policiesdeny by default	Entries12 tools
Workflow automations	Request & response inspectioninline	Content Types10 tools
Compatible MCP clients	Activity monitoringalerts and logs	All other tools47 tools