// SCAN REPORT

ConfigCat

72 tools. 38 can modify or destroy data without limits.

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

Last updated:

38 can modify or destroy data
34 read-only
72 tools total
// TOOL MAP
Read (34) Write / Execute (26) Destructive / Financial (12)
// WHAT CAN GO WRONG
✕

Destructive tools (delete-config, delete-environment, delete-integration) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

✕

Write operations (create-config, create-environment, create-integration) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

One command. Full control.

Intercept sits between your agent and ConfigCat. 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 @@configcat/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-config:
  rules:
    - action: deny

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

Rate limit write operations
create-config:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
get-code-references:
  rules:
    - rate_limit: 60/minute

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

// ALL 72 CONFIGCAT TOOLS
DESTRUCTIVE 12 tools
Destructive delete-config Destructive delete-environment Destructive delete-integration Destructive delete-invitation Destructive delete-organization-member Destructive delete-permission-group Destructive delete-product Destructive delete-product-member Destructive delete-segment Destructive delete-setting Destructive delete-tag Destructive delete-webhook
WRITE 26 tools
Write create-config Write create-environment Write create-integration Write create-permission-group Write create-product Write create-segment Write create-setting Write create-tag Write create-webhook Write invite-member Write post-setting-values Write replace-setting Write replace-setting-value Write replace-webhook Write update-config Write update-environment Write update-integration Write update-member-permissions Write update-permission-group Write update-product Write update-product-preferences Write update-segment Write update-setting Write update-setting-value Write update-tag Write update-webhook
READ 34 tools
Read get-code-references Read get-config Read get-environment Read get-integration Read get-permission-group Read get-product Read get-product-preferences Read get-sdk-keys Read get-segment Read get-setting Read get-setting-value Read get-setting-values Read get-tag Read get-webhook Read get-webhook-signing-keys Read list-auditlogs Read list-configs Read list-environments Read list-integrations Read list-organization-auditlogs Read list-organization-members Read list-organizations Read list-pending-invitations Read list-pending-invitations-org Read list-permission-groups Read list-product-members Read list-products Read list-segments Read list-settings Read list-settings-by-tag Read list-staleflags Read list-tags Read list-webhooks Read update-sdk-documentation
// FAQ
Can an AI agent delete data through the ConfigCat MCP server? +

Yes. The ConfigCat server exposes 12 destructive tools including delete-config, delete-environment, delete-integration. 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 ConfigCat? +

The ConfigCat server has 26 write tools including create-config, create-environment, create-integration. 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 ConfigCat MCP server expose? +

72 tools across 3 categories: Destructive, Read, Write. 34 are read-only. 38 can modify, create, or delete data.

How do I add Intercept to my ConfigCat setup? +

One line change. Instead of running the ConfigCat server directly, prefix it with Intercept: intercept -c configcat.yaml -- npx -y @@@configcat/mcp-server. Download a pre-built policy from policylayer.com/policies/configcat 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
admin
Aibtc 288 tools
admin
Google Super 200 tools
admin
Trello 200 tools
admin
Propresenter 177 tools
admin
Leaper Vision Toolkit 169 tools
admin
Apiosk 160 tools
admin
Mcp Sitecore 153 tools
admin
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.