Salesforce CLI MCP Server

38 tools. 22 can modify or destroy data without limits.

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

Last updated:

22 can modify or destroy data
16 read-only
38 tools total

Community server · catalogue entry verified 03/07/2026

How to control Salesforce CLI MCP Server ↓

What Salesforce CLI MCP Server exposes to your agents

Read (16) Write / Execute (20) Destructive / Financial (2)
Critical Risk

The most dangerous Salesforce CLI MCP Server tools

22 of Salesforce CLI MCP Server's 38 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Salesforce CLI MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and Salesforce CLI MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "delete_record": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

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

Rate limit write operations
{
  "assign_permission_set": {
    "limits": [
      {
        "counter": "assign_permission_set_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "apex_get_log": {
    "limits": [
      {
        "counter": "apex_get_log_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register Salesforce CLI MCP Server — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON SALESFORCE CLI →

Instant setup, no code required.

All 38 Salesforce CLI MCP Server tools

READ 16 tools
Read apex_get_log Fetch the specified log or given number of most recent logs from a project Read apex_log_list Fetch the list of apex debug logs from a project, returning the logs with their IDs. Read display_user Display information about a Salesforce user. Output includes the profile name, org ID, access token, instance Read execute_soql_query_tooling_api Execute a SOQL query against the Salesforce Tooling API from a project. This command allows you to query Sales Read get_apex_code_coverage Get code coverage information for a Salesforce Org from a project. This command allows you to retrieve org-wid Read get_apex_test_results Retrieve results from a previous asynchronous Apex test run from a project. Use this command with a test run I Read get_record Get a record from a Salesforce org from a project using the SF CLI. Retrieves all field values for the specifi Read list_code_analyzer_rules List the rules that are available to analyze your code from a project. You can also view details about the rul Read list_connected_salesforce_orgs List connected Salesforce Orgs. This command retrieves a list of all Salesforce Orgs that are currently connec Read list_metadata List the metadata components and properties of a specified type. Use this command to identify individual compo Read list_metadata_types Display details about the metadata types that are enabled for your org. The information includes Apex classes Read query_records Query records from a SINGLE Salesforce object from a project using structured field conditions. Use this for p Read query_records_to_file Query records from a Salesforce SObject from a project and save to a file. This command allows you to execute Read search_records Search for text across multiple Salesforce objects simultaneously from a project. USE THIS TOOL when searching Read sobject_describe Describe a Salesforce SObject from a project. This command retrieves detailed metadata about a specific Salesf Read sobject_list List all standard and custom objects in a Salesforce Org from a project. This command retrieves a list of all

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about Salesforce CLI MCP Server

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

Yes. The Salesforce CLI MCP Server server exposes 2 destructive tools including delete_record, package_uninstall. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Salesforce CLI MCP Server? +

The Salesforce CLI MCP Server server has 11 write tools including assign_permission_set, assign_permission_set_license, create_record. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Salesforce CLI MCP Server.

How many tools does the Salesforce CLI MCP Server MCP server expose? +

38 tools across 4 categories: Destructive, Execute, Read, Write. 16 are read-only. 22 can modify, create, or delete data.

How do I enforce a policy on Salesforce CLI MCP Server? +

Register the Salesforce CLI MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Salesforce CLI MCP Server tool call.

Deterministic rules across all 38 Salesforce CLI MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

38 Salesforce CLI MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.