How is this different from connecting Storyblok 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 Storyblok MCP API changes?

We track the Storyblok 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 Storyblok 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 Storyblok?

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 Storyblok MCP server myself?

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

Connect Storyblok MCP to your AI agents, securely.

Q: Is Storyblok MCP secure?

The server itself exposes 7 tools, and some of them can write to your Storyblok 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 Storyblok.

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

Get started for free

Get a demo

Try Storyblok MCP now

What your agents can ask once Storyblok MCP is connected.

Select the tools your AI agents can call

7 tools from the Storyblok MCP schema.

Showing 7 tools

searchreadDiscovers Management API operations by keyword, returning operation IDs, behavior hints, summaries and response fields.
describereadGets full parameter details for an operation, including parameter schemas and, for write operations, the request body schema.
execute_readonlyreadExecutes safe read operations (GET) against the Management API, for listing and fetching resources.
execute_mutatingwriteExecutes mutating operations (POST, PUT, PATCH) against the Management API, for creating and updating resources.
execute_destructivehigh riskExecutes DELETE operations against the Management API. Requires explicit confirmation from the user before use.
upload_assetwriteCreates an asset record and gets a signed S3 upload URL with a ready-to-use cURL command.
upload_asset_finishwriteFinalizes and validates the S3 asset upload once the file has been sent with the cURL command.

What Storyblok MCP exposes

Storyblok MCP groups its 7 tools into 3 categories, each with a suggested starting policy.

All 7 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Discovery	Searching Management API operations by keyword and describing an operation's parameters, request body schema and response fields	Read	Read-only and safe to allow broadly. It returns API documentation rather than space content, and it is the step that tells an agent which operationId it is about to run
Execution	Running any Management API operation by operationId, split by HTTP method: GET for reads, POST, PUT and PATCH for creates and updates, DELETE for deletions	Read / Write	The tool name only tells you the verb class, not the resource, so the policy has to look at the operationId and space_id in the arguments. Allow execute_readonly, gate execute_mutating to the operations the agent needs, and keep execute_destructive behind human approval
Assets	Creating an asset record with a signed S3 upload URL and cURL command, then finalizing and validating the upload	Read / Write	Writes new files into the space's asset library. Finishing the upload needs shell access to run the cURL command, so restrict it to agents that are meant to publish media

Connect Storyblok 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 Storyblok
Find Storyblok 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 Storyblok MCP or block it. You allow the exact tools each agent can call, one by one.

Storyblok MCP	7 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 7 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 Storyblok 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.	Storyblok MCP7 documented tools on the hosted, stateless HTTP server at mcp.storyblok.com. It exposes only the Management API, not the Content Delivery API, and authenticates with a Storyblok personal access token sent as a bearer token.
Coding assistants	Connection & credentialsper user	Execution3 tools
Internal copilots	Tool access policiesdeny by default	Discovery2 tools
Workflow automations	Request & response inspectioninline	Assets2 tools
Compatible MCP clients	Activity monitoringalerts and logs