Atlas / MCP servers / kiran1689 / Storyblok

StoryblokSAFE

Name: Storyblok
Author: kiran1689

mcp/kiran1689/storyblok-1

MCP server by kiran1689 · api · github · mcp · Audited 2026-10-08

A modular, extensible MCP Server for managing Storyblok spaces, stories, components, assets, workflows, and more via the Model Context Protocol (MCP).

Verdict

SAFE

Grade

Trust score

89 /100

Exposed tools

159 73r · 59w · 27d

Transport

stdio

License

MIT

Stars

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

The Storyblok MCP (Model Context Protocol) server enables your AI assistants to directly access and manage your Storyblok spaces, stories, components, assets, workflows, and more.

What Does It Do?

With the Storyblok MCP Server, your AI assistant can:

Create - Create new stories, components, assets, datasources, tags, releases, workflows, and more.
Read - Read all your stories, components, assets, datasources, tags, releases, workflows, and more.
Update - Update existing/new stories, components, assets, datasources, tags, releases, workflows, and more.
Delete - Delete specific/all your stories, components, assets, datasources, tags, releases, workflows, and more.

🚀 Features

Full Storyblok Management: CRUD for stories, components, assets, datasources, tags, releases, workflows, and more.(Covered everything)
Modular Tooling: Each Storyblok

Read from source at commit 5bbfcae73759OBSERVED · 2026-10-08

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code

claude mcp add storyblok-mcp-server --env STORYBLOK_DEFAULT_PUBLIC_TOKEN=${STORYBLOK_DEFAULT_PUBLIC_TOKEN} --env STORYBLOK_MANAGEMENT_TOKEN=${STORYBLOK_MANAGEMENT_TOKEN} -- uvx storyblok-mcp-server

claude-desktop

{
  "mcpServers": {
    "storyblok-mcp-server": {
      "command": "uvx",
      "args": [
        "storyblok-mcp-server"
      ],
      "env": {
        "STORYBLOK_DEFAULT_PUBLIC_TOKEN": "${STORYBLOK_DEFAULT_PUBLIC_TOKEN}",
        "STORYBLOK_MANAGEMENT_TOKEN": "${STORYBLOK_MANAGEMENT_TOKEN}"
      }
    }
  }
}

Exposed tools (159)

73 read · 59 write · 27 destructive. Blast radius: 27 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

Tool	Risk	Description
`add_webhook`	write
`ai_translate_story`	read
`backup_space`	read
`bulk_create_stories`	write	Creates multiple stories in Storyblok.
`bulk_delete_stories`	destructive	Deletes multiple stories in Storyblok.
`bulk_move_assets`	write
`bulk_publish_stories`	write	Publishes multiple stories by ID.
`bulk_restore_assets`	read
`bulk_update_stories`	write	Updates multiple stories in Storyblok, optionally publishing them.
`compare_story_versions`	read
`complete_asset_upload`	write	Completes the asset upload process after S3 upload.
`create_access_token`	write
`create_approval`	write
`create_asset_folder`	write
`create_branch`	write
`create_branch_deployment`	write
`create_comment`	write
`create_component`	write	#Creates a new component (block).
`create_component_folder`	write
`create_datasource`	write
`create_datasource_entry`	write
`create_discussion`	write
`create_extension`	write
`create_field_plugin`	write
`create_internal_tag`	write
`create_preset`	write
`create_release`	write
`create_release_approval`	write
`create_space`	write
`create_space_role`	write
`create_story`	write
`create_story_schedule`	write
`create_tag`	write
`create_task`	write
`create_workflow`	write
`create_workflow_stage`	write
`create_workflow_stage_change`	write
`debug_story_access`	read	Debug access to a specific story via various fetch parameters.
`delete_access_token`	destructive
`delete_approval`	destructive
`delete_asset`	destructive	Deletes an asset from Storyblok.
`delete_asset_folder`	destructive
`delete_branch`	destructive
`delete_collaborator`	destructive
`delete_comment`	destructive
`delete_component`	destructive	Deletes a component by ID.
`delete_component_folder`	destructive
`delete_datasource`	destructive
`delete_datasource_entry`	destructive
`delete_extension`	destructive
`delete_field_plugin`	destructive
`delete_internal_tag`	destructive
`delete_multiple_assets`	destructive
`delete_preset`	destructive
`delete_release`	destructive	Deletes a release.
`delete_space`	destructive
`delete_space_role`	destructive
`delete_story`	destructive	Deletes a story by ID.
`delete_story_schedule`	destructive
`delete_tag`	destructive	Deletes a tag from Storyblok.
`delete_task`	destructive
`delete_webhook`	destructive
`delete_workflow`	destructive
`delete_workflow_stage`	destructive
`duplicate_space`	read
`duplicate_workflow`	read
`fetch_asset_folder`	read
`fetch_assets`	read
`fetch_component_folders`	read
`fetch_components`	read	# Fetches components, optionally filtering and shaping the response.
`fetch_space_roles`	read
`fetch_spaces`	read
`fetch_stories`	read
`get_asset`	read	Gets a specific asset by ID.
`get_component`	read	Gets a specific component by ID.
`get_component_usage`	read	Finds stories where a component is used in content (draft & published).
`get_space`	read
`get_space_role`	read
`get_story`	read
`get_story_versions`	read
`get_unpublished_dependencies`	read
`init_asset_upload`	write	Initializes asset upload and returns signed S3 upload URL.
`list_tools`	read	Lists all available tools with their names, descriptions, and total count.
`ping`	read
`publish_story`	write
`resolve_discussion`	read
`restore_component_version`	read
`restore_story`	read	Restores a story to a specific version.
`retrieve_all_extension_settings`	read
`retrieve_all_extensions`	read
`retrieve_asset_folders`	read
`retrieve_component_versions`	read
`retrieve_extension`	read
`retrieve_extension_settings`	read
`retrieve_field_plugin`	read
`retrieve_field_plugins`	read
`retrieve_idea_discussions_comments`	read
`retrieve_multiple_access_tokens`	read
`retrieve_multiple_activities`	read
`retrieve_multiple_approvals`	read
`retrieve_multiple_branches`	read
`retrieve_multiple_collaborators`	read
`retrieve_multiple_comments`	read
`retrieve_multiple_datasource_entries`	read
`retrieve_multiple_datasources`	read
`retrieve_multiple_discussions`	read
`retrieve_multiple_internal_tags`	read
`retrieve_multiple_presets`	read
`retrieve_multiple_releases`	read
`retrieve_multiple_story_schedules`	read
`retrieve_multiple_tags`	read
`retrieve_multiple_tasks`	read
`retrieve_multiple_webhooks`	read
`retrieve_multiple_workflow_stage_changes`	read
`retrieve_multiple_workflow_stages`	read
`retrieve_multiple_workflows`	read
`retrieve_my_discussions`	read
`retrieve_one_story_schedule`	write
`retrieve_single_activity`	read
`retrieve_single_approval`	read
`retrieve_single_branch`	read
`retrieve_single_component_folder`	read
`retrieve_single_component_version`	read
`retrieve_single_datasource`	read
`retrieve_single_datasource_entry`	read
`retrieve_single_preset`	read
`retrieve_single_release`	read
`retrieve_single_task`	read
`retrieve_single_webhook`	read
`retrieve_single_workflow`	read
`retrieve_single_workflow_stage`	read
`retrieve_specific_discussion`	read
`tag_bulk_association`	read
`unpublish_story`	read
`update_access_token`	write
`update_asset`	write
`update_asset_folder`	write
`update_branch`	write
`update_collaborator`	write
`update_comment`	write
`update_component`	write	#Updates an existing component.
`update_component_folder`	write
`update_datasource`	write
`update_datasource_entry`	write
`update_extension`	write
`update_field_plugin`	write
`update_internal_tag`	write
`update_preset`	write
`update_release`	write
`update_space`	write
`update_space_role`	write
`update_story`	write
`update_story_schedule`	write
`update_tag`	write
`update_task`	write
`update_webhook`	write
`update_workflow`	write
`update_workflow_stage`	write
`validate_story_content`	read

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	PASS
L2	Instruction surface (what it tells the agent)	PASS
L3	Class-specific surface	WARN
L4	Behavioural (sandbox)	SKIPPED

What the source does

Filesystem: declared (1 observation(s))
Network: declared (2 observation(s))
Shell: none-observed
Dependencies: pinned
Secrets in source: none-found

Findings (3)

MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59

bulk_delete_stories, delete_access_token, delete_approval, delete_asset, delete_asset_folder, delete_branch, delete_collaborator, delete_comment, delete_component, delete_component_folder, delete_data

Why it matters. 27 tool(s) can delete or overwrite

Fix. prefer a read-only mode or scoped tokens; the page states the blast radius

LOWInventory / provenance · inv.binary · CWE-1104

requirements.txt

requirements.txt

Why it matters. a compiled or binary member cannot be reviewed from source

Fix. ship source, or explain the binary in the README

LOWPrompt injection · prompt.credential_read · CWE-94, CWE-1427

README.md:65

| Access Tokens              | Manage access tokens for Storyblok API           |

Why it matters. asks the agent to read credentials

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha 5bbfcae73759full audit observations/trust-audit/mcp-server/kiran1689__storyblok-1.json · Report an issue / request a re-scan

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

Date	Source	Verdict	Grade	Score	Change
2026-10-08	`5bbfcae73759`	SAFE	B	89	first audit

Questions

What is the Storyblok MCP server?

A modular, extensible MCP Server for managing Storyblok spaces, stories, components, assets, workflows, and more via the Model Context Protocol (MCP).

What tools does Storyblok expose?

159 in total: 73 read-only, 59 that write, and 27 that can delete or overwrite (bulk_delete_stories, delete_access_token, delete_approval, delete_asset, delete_asset_folder). Every one is listed on this page with its risk.

Is Storyblok safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 27 of its tools can destroy data, so scope the token you give it to what you actually need.

What credentials does Storyblok need?

It reads STORYBLOK_DEFAULT_PUBLIC_TOKEN and STORYBLOK_MANAGEMENT_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does Storyblok run?

It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as storyblok-mcp-server.

How current is this page?

The grade is for one exact copy of the source (5bbfcae73759), read on 2026-10-08. The repository is watched and re-audited when it changes.

Source	kiran1689/storyblok-mcp-server
PyPI	`storyblok-mcp-server`
Transports	stdio
Credentials it reads	`STORYBLOK_DEFAULT_PUBLIC_TOKENSTORYBLOK_MANAGEMENT_TOKEN`
License	MIT
Activity	pushed 473d ago