// SCAN REPORT

Salesforce

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

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

Last updated: 5 Apr 2026

19 can modify or destroy data

16 read-only

35 tools total

// TOOL MAP

Read (16) Write / Execute (18) Destructive / Financial (1)

// WHAT CAN GO WRONG

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

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

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

One command. Full control.

Intercept sits between your agent and Salesforce. 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 @@salesforce/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_org:
  rules:
    - action: deny

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

Rate limit write operations

assign_permission_set:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

checkCommitStatus:
  rules:
    - rate_limit: 60/minute

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

// ALL 35 SALESFORCE TOOLS

DESTRUCTIVE 1 tools

Destructive delete_org

EXECUTE 7 tools

Execute deploy_metadata Execute open_org Execute resume_tool_operation Execute run_agent_test Execute run_apex_test Execute run_code_analyzer Execute sfDevopsPromoteWorkItem

WRITE 11 tools

Write assign_permission_set Write create_mobile_lwc_native_capabilities Write create_org_snapshot Write create_scratch_org Write createPullRequest Write enable_tools Write sfDevopsCheckoutWorkItem Write sfDevopsCommitWorkItem Write sfDevopsCreateWorkItem Write sfDevopsResolveConflict Write sfDevopsUpdateWorkItemStatus

READ 16 tools

Read checkCommitStatus Read describe_code_analyzer_rule Read enrich_metadata Read get_mobile_lwc_offline_analysis Read get_mobile_lwc_offline_guidance Read get_username Read list_all_orgs Read list_code_analyzer_rules Read list_tools Read query_code_analyzer_results Read retrieve_metadata Read run_soql_query Read scan-apex-antipatterns Read sfDevopsDetectConflict Read sfDevopsListProjects Read sfDevopsListWorkItems

// FAQ

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

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

The Salesforce server has 11 write tools including assign_permission_set, create_mobile_lwc_native_capabilities, create_org_snapshot. 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 MCP server expose? +

35 tools across 4 categories: Destructive, Execute, Read, Write. 16 are read-only. 19 can modify, create, or delete data.

How do I add Intercept to my Salesforce setup? +

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

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.