// SCAN REPORT

Salesforce Cloud

17 tools. 6 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 4 Apr 2026

6 can modify or destroy data

11 read-only

17 tools total

// TOOL MAP

Read (11) Write / Execute (5) Destructive / Financial (1)

// WHAT CAN GO WRONG

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

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

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

One command. Full control.

Intercept sits between your agent and Salesforce Cloud. 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 @aaronsb/salesforce-cloud-mcp

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_record:
  rules:
    - action: deny

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

Rate limit write operations

create_record:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

analyze:
  rules:
    - rate_limit: 60/minute

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

// ALL 17 SALESFORCE CLOUD TOOLS

DESTRUCTIVE 1 tools

Destructive delete_record

EXECUTE 2 tools

Execute batch Execute execute_soql

WRITE 3 tools

Write create_record Write generate_business_case Write update_record

READ 11 tools

Read analyze Read analyze_conversation Read describe_object Read download_file Read enrich_opportunity Read find_similar_opportunities Read get_opportunity_details Read get_user_info Read list_objects Read opportunity_insights Read search_opportunities

// FAQ

Can an AI agent delete data through the Salesforce Cloud MCP server? +

Yes. The Salesforce Cloud server exposes 1 destructive tools including delete_record. 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 Salesforce Cloud? +

The Salesforce Cloud server has 3 write tools including create_record, generate_business_case, update_record. 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 Cloud MCP server expose? +

17 tools across 4 categories: Destructive, Execute, Read, Write. 11 are read-only. 6 can modify, create, or delete data.

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

One line change. Instead of running the Salesforce Cloud server directly, prefix it with Intercept: intercept -c salesforce-cloud.yaml -- npx -y @@aaronsb/salesforce-cloud-mcp. Download a pre-built policy from policylayer.com/policies/salesforce-cloud 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.

Salesforce Cloud

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.