generate_pipeline · Pipeline Assistant MCP: Risk & Policy

WHAT IT DOES

What generate_pipeline does on Pipeline Assistant MCP

AI agents use generate_pipeline to create or update resources in Pipeline Assistant MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pipeline Assistant MCP environment.

WHY IT NEEDS A POLICY

Why generate_pipeline needs a policy

The tool generates/creates a CI/CD pipeline configuration from templates and corporate standards. This is a Write operation as it produces new configuration artifacts. It does not appear to execute the pipeline itself, delete data, or involve financial transactions.

From the tool's definition 'Genera un pipeline CI/CD' (Generates a CI/CD pipeline) based on corporate wiki standards — implies creation of a new pipeline configuration artifact

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

generate_pipeline Rate-limited

generate_pipeline stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "generate_pipeline": {
      "limits": [
        {
          "counter": "generate_pipeline_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about generate_pipeline

What does the generate_pipeline tool do? +

Genera un pipeline CI/CD basado en estándares corporativos de la wiki. It is categorised as a Write tool in the Pipeline Assistant MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on generate_pipeline? +

Register the Pipeline Assistant MCP server in PolicyLayer and add a rule for generate_pipeline: 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 Pipeline Assistant MCP. Nothing to install.

What risk level is generate_pipeline? +

generate_pipeline is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit generate_pipeline? +

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

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

generate_pipeline is provided by the Pipeline Assistant MCP server (soydachi/pipeline-assistant-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.