run_manual_check

THE RISK

High Risk

Why run_manual_check needs a policy

This tool executes a compliance check, which is a process whose side effects depend on arguments (which control is checked, what the check validates). While it does not permanently destroy data or move money, it actively triggers operations rather than passively retrieving data. The 'Execute' category applies because the tool runs (initiates) a process.

From the tool's definition Tool name 'run_manual_check' and description 'Run a manual compliance check for a control' indicate execution of a checking/validation operation. The verb 'run' combined with 'manual check' suggests triggering an automated workflow or process.

Documented attack patterns abuse exactly the kind of access run_manual_check gives an agent:

POLICY

How to control run_manual_check

PolicyLayer is an MCP gateway — it sits between your AI agents and NIST MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for run_manual_check:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_manual_check": {
      "limits": [
        {
          "counter": "run_manual_check_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

run_manual_check 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.

Create a free account and register NIST MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More NIST MCP Server tools

Execute execute_compliance_workflow Execute an automated compliance workflow (Strand) Execute start_continuous_monitoring Start continuous monitoring for a specific control Execute stop_continuous_monitoring Stop continuous monitoring for a control Write create_remediation_action Create a remediation action for a control Write gap_analysis_with_history Perform gap analysis and save results to history with optional remediation planning Write register_connector Register a new connector for external system integration Write save_assessment Save assessment results to history Write update_remediation_status Update the status of a remediation action

All 44 NIST MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in NIST MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about run_manual_check

What does the run_manual_check tool do? +

Run a manual compliance check for a control. It is categorised as a Execute tool in the NIST MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_manual_check? +

Register the NIST MCP Server MCP server in PolicyLayer and add a rule for run_manual_check: 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 NIST MCP Server. Nothing to install.

What risk level is run_manual_check? +

run_manual_check is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_manual_check? +

Yes. Add a rate_limit block to the run_manual_check 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.

How do I block run_manual_check completely? +

Set action: deny in the PolicyLayer policy for run_manual_check. 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.

What MCP server provides run_manual_check? +

run_manual_check is provided by the NIST MCP Server MCP server (tnicholson/nist-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every NIST MCP Server tool call.

Start from NIST MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →