// SCAN REPORT

Ljit Mcp Sfmc

30 tools. 19 can modify or destroy data without limits.

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

Last updated: 20 Apr 2026

19 can modify or destroy data

11 read-only

30 tools total

// TOOL MAP

Read (11) Write / Execute (17) Destructive / Financial (2)

// WHAT CAN GO WRONG

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

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

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

One command. Full control.

Intercept sits between your agent and Ljit Mcp Sfmc. 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 @ljit-mcp-sfmc

Scans every tool. Generates a policy. Starts enforcing.

Works with Claude Code · Cursor · Claude Desktop · Windsurf · any MCP client

// RECOMMENDED RULES

Deny destructive operations

cb_delete_asset:
  rules:
    - action: deny

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

Rate limit write operations

cb_create_asset:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

cb_get_asset:
  rules:
    - rate_limit: 60/minute

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

// ALL 30 LJIT MCP SFMC TOOLS

DESTRUCTIVE 2 tools

Destructive cb_delete_asset Destructive txn_delete_definition

EXECUTE 1 tools

Execute txn_preflight_email

WRITE 16 tools

Write cb_create_asset Write cb_create_folder Write cb_update_asset Write de_create Write de_upsert_rows Write txn_create_email_definition Write txn_create_push_definition Write txn_create_sms_definition Write txn_send_email Write txn_send_email_and_check Write txn_send_email_batch Write txn_send_push Write txn_send_sms Write txn_send_sms_batch Write txn_send_test_email Write txn_update_definition

READ 11 tools

Read cb_get_asset Read cb_list_assets Read cb_list_folders Read de_get_info Read de_list Read de_list_rows Read txn_get_definition Read txn_get_message_status Read txn_inspect_email_definition Read txn_list_definitions Read txn_validate_email_attributes

// FAQ

Can an AI agent delete data through the Ljit Mcp Sfmc MCP server? +

Yes. The Ljit Mcp Sfmc server exposes 2 destructive tools including cb_delete_asset, txn_delete_definition. 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 Ljit Mcp Sfmc? +

The Ljit Mcp Sfmc server has 16 write tools including cb_create_asset, cb_create_folder, cb_update_asset. 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 Ljit Mcp Sfmc MCP server expose? +

30 tools across 4 categories: Destructive, Execute, Read, Write. 11 are read-only. 19 can modify, create, or delete data.

How do I add Intercept to my Ljit Mcp Sfmc setup? +

One line change. Instead of running the Ljit Mcp Sfmc server directly, prefix it with Intercept: intercept -c ljit-mcp-sfmc.yaml -- npx -y @ljit-mcp-sfmc. Download a pre-built policy from policylayer.com/policies/ljit-mcp-sfmc 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.

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.

Ljit Mcp Sfmc

One command. Full control.

Other MCP servers with similar tools.

Control every MCP tool call your agent makes.

Control every MCP tool call
your agent makes.