Atlas / MCP servers / advancedcommunities / Salesforce

SalesforceBLOCK

mcp/advancedcommunities/salesforce-11

MCP server that enables AI assistants to interact with Salesforce orgs through the Salesforce CLI, providing tools for Apex execution, SOQL queries, metadata management, code analysis, and development automation.

Verdict
BLOCK
Grade
D
Trust score
64 /100
Exposed tools
40 23r · 14w · 3d
Transport
stdio
License
MIT
Stars
35
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://www.npmjs.com/package/@advanced-communities/salesforce-mcp-server) [](https://www.npmjs.com/package/@advanced-communities/salesforce-mcp-server) [](https://github.com/advancedcommunities/salesforce-mcp-server/releases) [](https://github.com/advancedcommunities/salesforce-mcp-server/blob/main/LICENSE)

What is it

Salesforce MCP Server is a Model Context Protocol (MCP) server that enables AI assistants to interact with Salesforce organizations. It provides a set of tools that allow AI models to execute Apex code, query data, describe objects, and manage Salesforce org connections through the Salesforce CLI.

NPM Package: @advanced-communities/salesforce-mcp-server

Installation

Prerequisites

Option 1: NPM Installation (Recommended)

The easiest way to install Salesforce MCP Server is directly from NPM using npx:

npx @advanced-communities/salesforce-mcp-server

This command will:

  • Download the latest version from NPM
  • Run the server directly without manual installation
  • Automatically handle all dependencies

Benefits of NPM Installation:

  • ✅ No manual building required
  • ✅ Always get the latest stable version
  • ✅ Automatic dependency management
  • ✅ Easy updates with npm update
  • ✅ No need to clone the repository

Option 2: MCP Bundle

Read from source at commit 41e571bc9836OBSERVED · 2026-10-08
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code (npm)
claude mcp add salesforce-mcp-server -- npx -y @advanced-communities/[email protected]
03

Exposed tools (40)

23 read · 14 write · 3 destructive. Blast radius: 3 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

ToolRiskDescription
apex_get_logread
apex_log_listread
assign_permission_setwrite
assign_permission_set_licensewrite
clear_default_orgdestructive
create_recordwrite
delete_recorddestructive
deploy_startwrite
display_userread
execute_anonymous_apexwrite
generate_classread
generate_componentread
generate_triggerwrite
get_apex_code_coverageread
get_apex_test_resultsread
get_default_orgread
get_server_permissionsread
install_skillwrite
list_code_analyzer_rulesread
list_connected_salesforce_orgsread
list_metadataread
list_metadata_typesread
login_into_orgread
logoutread
openread
open_recordread
package_installwrite
package_uninstalldestructive
query_recordsread
query_records_to_fileread
run_apex_testswrite
run_code_analyzerwrite
scanner_runwrite
scanner_run_dfawrite
schema_generate_tabread
search_recordsread
set_default_orgwrite
sobject_describeread
sobject_listread
update_recordwrite
04

Trust audit

BLOCKgrade D · trust 64/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeFAIL
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfaceWARN
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (3 observation(s))
Network
declared (1 observation(s))
Shell
declared (4 observation(s))
Dependencies
not all pinned
Secrets in source
none-found

Findings (11)

HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
scripts/verify-command-injection-fix.mjs:26
exec(command, (error, stdout, stderr) =>
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
src/tools/records.ts:261
exec(command, (error, stdout, stderr) => {
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
src/utils/sfCommand.ts:61
exec(
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
src/utils/sfCommand.ts:122
exec(
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
MEDIUMFilesystem / path · fs.system_paths · CWE-22, CWE-59
src/utils/sfCommand.ts:10
"/usr/local/bin/sf",
MEDIUMFilesystem / path · fs.system_paths · CWE-22, CWE-59
src/utils/sfCommand.ts:16
"/usr/local/bin/sf",
MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59
clear_default_org, delete_record, package_uninstall
Why it matters. 3 tool(s) can delete or overwrite
Fix. prefer a read-only mode or scoped tokens; the page states the blast radius
LOWCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
test/shellEscape.test.mjs:69
"posixQuote: exec() (the sfCommand.ts path) does not run injected commands",
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
@modelcontextprotocol/sdk, @salesforce/apex-node, @salesforce/core, zod, @anthropic-ai/mcpb, @types/node, typescript
Why it matters. 7 dependency range(s) float
Fix. pin exact versions or ship a lockfile
INFOPrompt injection · prompt.authority_framing · CWE-94, CWE-1427
README.MD:360
**Full access to specific orgs only:**
INFOPrompt injection · prompt.credential_read · CWE-94, CWE-1427
CHANGELOG.md:30
- Users migrating from `generate_frontdoor_url` should use `open` with `USE_CLIENT_BROWSER=true` environment variable
Why it matters. asks the agent to read credentials

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha 41e571bc9836full audit observations/trust-audit/mcp-server/advancedcommunities__salesforce-11.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-0841e571bc9836BLOCKD64first audit
06

Questions

What is the Salesforce MCP server?

MCP server that enables AI assistants to interact with Salesforce orgs through the Salesforce CLI, providing tools for Apex execution, SOQL queries, metadata management, code analysis, and development automation.

What tools does Salesforce expose?

40 in total: 23 read-only, 14 that write, and 3 that can delete or overwrite (clear_default_org, delete_record, package_uninstall). Every one is listed on this page with its risk.

Is Salesforce safe to connect to an agent?

No — not without reading the findings first. The audit graded it D (64/100) and found 4 critical or high issues in the source. Each one is listed on this page with the file and line it is on. Separately from the audit: 3 of its tools can destroy data, so scope the token you give it to what you actually need.

What credentials does Salesforce need?

It reads SFMCP_TEST_SECRET from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.

How does Salesforce run?

It speaks stdio, so it runs as a local process your client starts. It is published on npm as @advanced-communities/salesforce-mcp-server at 1.7.0.

How current is this page?

The grade is for one exact copy of the source (41e571bc9836), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement