Salesforce Marketing

47 tools. 14 can modify or destroy data without limits.

14 write tools that can modify data. Rate limits recommended.

Last updated:

14 can modify or destroy data
33 read-only
47 tools total
Read (33) Write / Execute (14) Destructive / Financial (0)

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

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

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

Prevents bulk unintended modifications from agents caught in loops.

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

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

How do I prevent bulk modifications through Salesforce Marketing? +

The Salesforce Marketing server has 11 write tools including sf_add_campaign_member, sf_bulk_add_campaign_members, sf_convert_lead. 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 Salesforce Marketing MCP server expose? +

47 tools across 3 categories: Execute, Read, Write. 33 are read-only. 14 can modify, create, or delete data.

How do I add Intercept to my Salesforce Marketing setup? +

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

Other MCP servers with similar tools.

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

Let agents act without letting them run wild.

Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.