cortex_pipeline_start · Cortex MCP: Risk & Policy

WHAT IT DOES

What cortex_pipeline_start does on Cortex MCP

AI agents invoke cortex_pipeline_start to trigger actions in Cortex 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 IT NEEDS A POLICY

Why cortex_pipeline_start needs a policy

This tool initiates automated execution of arbitrary tasks derived from user-provided goals. While it does not inherently delete data (Destructive) or move money (Financial), it triggers external operations and code execution autonomously with retry logic. The blast radius depends on what tasks are generated from the goal; a poorly specified goal could cause unintended side effects.

From the tool's definition Tool description states it 'Breaks goal into tasks, executes them, auto-retries failures' — the verb 'executes' combined with 'autonomous pipeline' indicates the tool runs operations whose effects depend on the goal/tasks provided.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cortex_pipeline_start Rate-limited

cortex_pipeline_start 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": {
    "cortex_pipeline_start": {
      "limits": [
        {
          "counter": "cortex_pipeline_start_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 Cortex MCP, so you can run agents against it safely.

FAQ

Questions about cortex_pipeline_start

What does the cortex_pipeline_start tool do? +

Start an autonomous pipeline from a goal. Breaks goal into tasks, executes them, auto-retries failures. It is categorised as a Execute tool in the Cortex MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on cortex_pipeline_start? +

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

What risk level is cortex_pipeline_start? +

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

Can I rate-limit cortex_pipeline_start? +

Yes. Add a rate_limit block to the cortex_pipeline_start 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 cortex_pipeline_start completely? +

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

cortex_pipeline_start is provided by the Cortex MCP server (neuralnexustech/cortex-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.