list-runs

List recent code execution runs for potential save-as-photon conversion

SERVERNcp SOURCE@portel/ncp

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-portel-dev-ncp/list-runs.md

WHAT IT DOES

What list-runs does on Ncp

AI agents call list-runs to retrieve information from Ncp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why list-runs is rated Low

This tool retrieves historical data about code execution runs without modifying, deleting, or triggering new actions. It is a read-only operation that returns information for review or audit purposes, with no side effects on the underlying systems.

From the tool's definition Tool name 'list-runs' and description 'List recent code execution runs' indicate a query/retrieval operation with no modification or destructive capability.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs list-runs safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Ncp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For list-runs, this is the rule to start with:

list-runs Allowed

list-runs is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "list-runs": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Ncp, apply this rule, and every list-runs call is checked against it from then on.

FAQ

Questions about list-runs

What does the list-runs tool do? +

List recent code execution runs for potential save-as-photon conversion. It is categorised as a Read tool in the Ncp MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on list-runs? +

Register the Ncp MCP server in PolicyLayer and add a rule for list-runs: 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 Ncp. Nothing to install.

What risk level is list-runs? +

list-runs is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit list-runs? +

Yes. Add a rate_limit block to the list-runs 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 list-runs completely? +

Set action: deny in the PolicyLayer policy for list-runs. 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 list-runs? +

list-runs is provided by the Ncp MCP server (@portel/ncp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Ncp, and thousands of servers like it.

This server

All 275 Ncp tools →

Across the catalogue

aiva_list_affiliates on AIVA MCP Server →list_agents on 0rca Dojo MCP Server → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →