run_complete_analysis · StatFlow MCP: Risk & Policy

WHAT IT DOES

What run_complete_analysis does on StatFlow

AI agents invoke run_complete_analysis to trigger actions in StatFlow. 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 IT NEEDS A POLICY

Why run_complete_analysis needs a policy

This tool orchestrates a complex, multi-step workflow that executes analysis operations across multiple systems (databases, Excel generation, Word document creation). While it primarily reads data and writes output files, the execution of analysis logic and potential for unintended consequences through misconfigured databases or incorrect parameters makes it Execute-category.

From the tool's definition Tool description states it 'Run[s] the entire experiment analysis from start to finish' and 'Fetches data from all configured databases → Generates Excel with comprehensive analysis tables → Creates thesis-quality Word report.' The verb 'Run' combined with…

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_complete_analysis Rate-limited

run_complete_analysis 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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches StatFlow, so you can run agents against it safely.

FAQ

Questions about run_complete_analysis

What does the run_complete_analysis tool do? +

🎯 COMPLETE WORKFLOW: Run the entire experiment analysis from start to finish. Fetches data from all configured databases → Generates Excel with comprehensive analysis tables → Creates thesis-quality Word report. This is the all-in-one tool. It is categorised as a Execute tool in the StatFlow 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_complete_analysis? +

Register the StatFlow MCP server in PolicyLayer and add a rule for run_complete_analysis: 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 StatFlow. Nothing to install.

What risk level is run_complete_analysis? +

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

Can I rate-limit run_complete_analysis? +

Yes. Add a rate_limit block to the run_complete_analysis 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_complete_analysis completely? +

Set action: deny in the PolicyLayer policy for run_complete_analysis. 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_complete_analysis? +

run_complete_analysis is provided by the StatFlow MCP server (rucha-nandgirikar/statflow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.