comment_on_work_item

SERVERStarfield SOURCE@adrata/starfield-mcp

Medium RISK CLASS

Category Write

Parameters 62 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/adrata-starfield-mcp/comment-on-work-item.md

WHAT IT DOES

What comment_on_work_item does on Starfield

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

Parameter	Type	Required	Description
`body`	string	Yes	What you want to say. Plain text; newlines are kept. Capped at 2000 characters — longer than that belongs in the card description or a linked document. Use `<@u
`dryRun`	boolean	—	Defaults to true. Set false to post it.
`itemId`	string	Yes	Card id.
`reason`	string	—	Required for a live post: why you are commenting. This is the audit reason, NOT the comment — the comment is `body`.
`approved`	boolean	—	Required true for a live post.
`idempotencyKey`	string	—	Required for a live post. Reuse the SAME key on retry: a replayed comment is just the same paragraph twice, which reads as you being emphatic rather than as a r

Parameters from the server's own tool schema.

RISK

Why comment_on_work_item is rated Medium

An AI agent can call comment_on_work_item faster than any human can review: one bad instruction and it creates or modifies resources in Starfield by the hundred, each call as confident as the last.

Risk signalsAccepts raw HTML/template content (body)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs comment_on_work_item safely

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

comment_on_work_item Rate-limited

comment_on_work_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": {
    "comment_on_work_item": {
      "limits": [
        {
          "counter": "comment_on_work_item_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

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

FAQ

Questions about comment_on_work_item

What does the comment_on_work_item tool do? +

Say something on a card: a question, a finding, or the reason a QA pass sent it back. This is the ONLY place to put a fact that contradicts the card — the ship-the-card skill tells you to say so on the card rather than silently fixing something else, and this is where that goes. Do NOT overwrite the card's body to make the point: the body is the original request, and rewriting it destroys the evidence of what was actually asked for. A comment is deliberately small: no threading, no reactions, no formatting. One author, one paragraph, in order. TO @-MENTION SOMEBODY, write the token <@userId> in the body — the id comes from the card's assignee, its history, or list_my_work_items. Anything else you type is literal text: writing "@noah" mentions nobody, which is deliberate. A mention means "see this" and NOTHING more — it does not assign the card, add a watcher, or raise a flag. Only workspace members resolve; a token naming anyone else stays as text and notifies no one. Governed write: previews by default. A live write requires dryRun:false plus approved:true, a reason, and an idempotencyKey (reuse the SAME key on retry — a duplicate move would read as the card having bounced between columns). It is categorised as a Write tool in the Starfield MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does comment_on_work_item accept? +

comment_on_work_item accepts 6 parameters: body, dryRun, itemId, reason, approved, idempotencyKey. Required: body, itemId. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on comment_on_work_item? +

Register the Starfield MCP server in PolicyLayer and add a rule for comment_on_work_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 Starfield. Nothing to install.

What risk level is comment_on_work_item? +

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

Can I rate-limit comment_on_work_item? +

Yes. Add a rate_limit block to the comment_on_work_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 comment_on_work_item completely? +

Set action: deny in the PolicyLayer policy for comment_on_work_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 comment_on_work_item? +

comment_on_work_item is provided by the Starfield MCP server (@adrata/starfield-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Starfield, and thousands of servers like it.

This server

All 233 Starfield tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →