run_agent_across_list

THE RISK

High Risk

Why run_agent_across_list needs a policy

This tool triggers execution of AI coding agents (Claude, Gemini, Codex) across arbitrary lists of items. While the agents themselves are not user code, the tool orchestrates their execution to perform code analysis, refactoring, and generation tasks whose side effects depend entirely on the prompt provided. The 'automatic permission skipping' suggests reduced safety constraints.

From the tool's definition 'Spawns an AI coding agent for each item in a previously created list. Agents run in batches of ${BATCH_SIZE} parallel processes' - spawning and executing agents that perform code analysis, refactoring, or generation constitutes execution of external…

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

POLICY

How to control run_agent_across_list

PolicyLayer is an MCP gateway — it sits between your AI agents and Par5, and nothing reaches the server without passing your rules. This is the rule we recommend for run_agent_across_list:

policy.json

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

run_agent_across_list 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 Par5 — 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 Par5 tools

Destructive delete_list Deletes an existing list by its ID. WHEN TO USE: - To clean up lists that are no longer n Execute run_shell_across_list Executes a shell command for each item in a previously created list. Commands run in batch Execute create_list_from_shell Creates a list by running a shell command and parsing its newline-delimited output. WHEN Write create_list Creates a named list of items for parallel processing. Use this tool when you need to perf Write update_list Updates an existing list by replacing its items with a new array. WHEN TO USE: - To modif Read get_list Retrieves the items in an existing list by its ID. WHEN TO USE: - To inspect the contents Read list_all_lists Lists all existing lists and their item counts. WHEN TO USE: - To see all available lists

All 8 Par5 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 Par5 → 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_agent_across_list

What does the run_agent_across_list tool do? +

Spawns an AI coding agent for each item in a previously created list. Agents run in batches of ${BATCH_SIZE} parallel processes with automatic permission skipping enabled. WHEN TO USE: - Performing complex code analysis, refactoring, or generation across multiple files - Tasks that require AI reasoning rather than simple shell commands - When you need to delegate work to multiple AI agents working in parallel AVAILABLE AGENTS: ${availableAgentsDoc} HOW IT WORKS: 1. Each item in the list is substituted into the prompt where {{item}} appears 2. Agents run in batches of ${BATCH_SIZE} at a time to avoid overwhelming the system 3. Output streams directly to files as the agents work 4. This tool waits for all agents to complete before returning AFTER COMPLETION: - Read the stdout files to check the results from each agent - Check stderr files if you encounter errors - Files are named based on the item (e.g.,. It is categorised as a Execute tool in the Par5 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_agent_across_list? +

Register the Par5 MCP server in PolicyLayer and add a rule for run_agent_across_list: 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 Par5. Nothing to install.

What risk level is run_agent_across_list? +

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

Can I rate-limit run_agent_across_list? +

Yes. Add a rate_limit block to the run_agent_across_list 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_agent_across_list completely? +

Set action: deny in the PolicyLayer policy for run_agent_across_list. 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_agent_across_list? +

run_agent_across_list is provided by the Par5 MCP server (mathematic-inc/par5-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

What run_agent_across_list does on Par5