write_pipeline_item · Pelaris MCP: Risk & Policy

WHAT IT DOES

What write_pipeline_item does on Pelaris

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

WHY IT NEEDS A POLICY

Why write_pipeline_item needs a policy

This is a Write operation: it creates or modifies data within a fitness/coaching pipeline without irreversible deletion or destruction. The blast radius is medium because while the tool modifies user fitness coaching data (programs, sessions, plans), these changes are reversible and don't directly execute external code or commit financial transactions.

From the tool's definition 'Create or update a content pipeline item' - the tool explicitly creates new entries and modifies existing ones in a pipeline, with reversible changes controlled by the ID parameter (update if provided, create if omitted).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

write_pipeline_item Rate-limited

write_pipeline_item 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": {
    "write_pipeline_item": {
      "limits": [
        {
          "counter": "write_pipeline_item_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 Pelaris, so you can run agents against it safely.

FAQ

Questions about write_pipeline_item

What does the write_pipeline_item tool do? +

Create or update a content pipeline item. Provide an ID to update, omit to create. It is categorised as a Write tool in the Pelaris MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on write_pipeline_item? +

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

What risk level is write_pipeline_item? +

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

Can I rate-limit write_pipeline_item? +

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

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

write_pipeline_item is provided by the Pelaris MCP server (thedonk/pelaris-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.