// SCAN REPORT

Contentful

61 tools. 36 can modify or destroy data without limits.

12 destructive tools with no built-in limits. Policy required.

Last updated:

36 can modify or destroy data
25 read-only
61 tools total
// TOOL MAP
Read (25) Write / Execute (24) Destructive / Financial (12)
// WHAT CAN GO WRONG
✕

Destructive tools (delete_ai_action, delete_asset, delete_concept) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

✕

Write operations (create_ai_action, create_concept, create_concept_scheme) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

✕

Execute tools (invoke_ai_action) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.

One command. Full control.

Intercept sits between your agent and Contentful. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.

npx -y @policylayer/intercept scan -- npx -y @@contentful/mcp-server
Scans every tool. Generates a policy. Starts enforcing.
Works with Claude Code · Cursor · Claude Desktop · Windsurf · any MCP client
// RECOMMENDED RULES
Deny destructive operations
delete_ai_action:
  rules:
    - action: deny

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
create_ai_action:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
get_ai_action:
  rules:
    - rate_limit: 60/minute

Controls API costs and prevents retry loops from exhausting upstream rate limits.

// ALL 61 CONTENTFUL TOOLS
DESTRUCTIVE 12 tools
Destructive delete_ai_action Destructive delete_asset Destructive delete_concept Destructive delete_concept_scheme Destructive delete_content_type Destructive delete_entry Destructive delete_environment Destructive delete_locale Destructive unpublish_ai_action Destructive unpublish_asset Destructive unpublish_content_type Destructive unpublish_entry
EXECUTE 1 tools
Execute invoke_ai_action
WRITE 23 tools
Write create_ai_action Write create_concept Write create_concept_scheme Write create_content_type Write create_entry Write create_environment Write create_locale Write create_tag Write export_space Write publish_ai_action Write publish_asset Write publish_content_type Write publish_entry Write space_to_space_migration_handler Write update_ai_action Write update_asset Write update_concept Write update_concept_scheme Write update_content_type Write update_editor_interface Write update_entry Write update_locale Write upload_asset
READ 25 tools
Read get_ai_action Read get_ai_action_invocation Read get_asset Read get_concept Read get_concept_scheme Read get_content_type Read get_editor_interface Read get_entry Read get_initial_context Read get_locale Read get_org Read get_space Read list_ai_actions Read list_assets Read list_concept_schemes Read list_concepts Read list_content_types Read list_editor_interfaces Read list_environments Read list_locales Read list_orgs Read list_spaces Read list_tags Read search_entries Read space_to_space_param_collection
// FAQ
Can an AI agent delete data through the Contentful MCP server? +

Yes. The Contentful server exposes 12 destructive tools including delete_ai_action, delete_asset, delete_concept. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Contentful? +

The Contentful server has 23 write tools including create_ai_action, create_concept, create_concept_scheme. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.

How many tools does the Contentful MCP server expose? +

61 tools across 4 categories: Destructive, Execute, Read, Write. 25 are read-only. 36 can modify, create, or delete data.

How do I add Intercept to my Contentful setup? +

One line change. Instead of running the Contentful server directly, prefix it with Intercept: intercept -c contentful.yaml -- npx -y @@@contentful/mcp-server. Download a pre-built policy from policylayer.com/policies/contentful and adjust the limits to match your use case.

// RELATED SERVERS

Other MCP servers with similar tools.

Starter policies available for each. Same risk classification, same one-command setup.

Mcp Api 310 tools
adminautomation
Aibtc 288 tools
adminautomation
Google Super 200 tools
adminautomation
Propresenter 177 tools
adminautomation
Leaper Vision Toolkit 169 tools
adminautomation
Apiosk 160 tools
adminautomation
Mcp Sitecore 153 tools
adminautomation
SmartBear MCP 147 tools
adminautomation
policylayer/intercept

Control every MCP tool call
your agent makes.

Set budgets, approvals, and hard limits across MCP servers.

npx -y @policylayer/intercept init
Protect your agent in 30 seconds. Scans your MCP config and generates enforcement policies for every server.
// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.