sf_run_apex_tests
Runs one or more Apex test classes and returns pass/fail results with any error messages. Uses the Salesforce Tooling API runTestsAsynchronous endpoint and polls for results. Use after deploying Apex code to verify test coverage, or to run regression tests before a release.
This record as markdown: /tools/io-github-semwalajay83-sem-salesforce-metadata-mcp/sf-run-apex-tests.md
What sf_run_apex_tests does on Salesforce Metadata Mcp
AI agents invoke sf_run_apex_tests to trigger actions in Salesforce Metadata Mcp. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why sf_run_apex_tests is rated High
Although test execution is non-destructive and read-like in intent, the tool actively runs arbitrary Apex test code in a Salesforce org, which is an Execute action. Apex tests can have side effects (creating test data, calling external APIs, modifying org state during test setup). An agent misusing this tool by running tests with unintended side effects or in the wrong org context poses operational risk.
From the tool's definition 'Runs one or more Apex test classes' and 'Uses the Salesforce Tooling API runTestsAsynchronous endpoint' — this tool executes code (Apex test execution) whose effects depend on what tests are supplied as arguments.
Attacks that exploit this kind of access
The rule that runs sf_run_apex_tests safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Salesforce Metadata Mcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For sf_run_apex_tests, this is the rule to start with:
sf_run_apex_tests stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Salesforce Metadata Mcp, apply this rule, and every sf_run_apex_tests call is checked against it from then on.
Questions about sf_run_apex_tests
Runs one or more Apex test classes and returns pass/fail results with any error messages. Uses the Salesforce Tooling API runTestsAsynchronous endpoint and polls for results. Use after deploying Apex code to verify test coverage, or to run regression tests before a release. It is categorised as a Execute tool in the Salesforce Metadata Mcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Salesforce Metadata MCP server in PolicyLayer and add a rule for sf_run_apex_tests: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Salesforce Metadata Mcp. Nothing to install.
sf_run_apex_tests is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the sf_run_apex_tests rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for sf_run_apex_tests. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
sf_run_apex_tests is provided by the Salesforce Metadata MCP server (salesforce-metadata-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Salesforce Metadata, and thousands of servers like it.
Across the catalogue