set_work_item_kind

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/set-work-item-kind.md

WHAT IT DOES

What set_work_item_kind does on Starfield

AI agents use set_work_item_kind 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
`kind`	object	Yes	bug \| story \| chore, or null to clear it back to untyped. "story", not "feature" — that was the old tag-scheme spelling and the API rejects it.
`dryRun`	boolean	—	Defaults to true. Set false for a live change.
`itemId`	string	Yes	Card id.
`reason`	string	—	Required for a live change: why this kind.
`approved`	boolean	—	Required true for a live change.
`idempotencyKey`	string	—	Required for a live change.

Parameters from the server's own tool schema.

RISK

Why set_work_item_kind is rated Medium

An AI agent can call set_work_item_kind 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.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs set_work_item_kind 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 set_work_item_kind, this is the rule to start with:

set_work_item_kind Rate-limited

set_work_item_kind 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": {
    "set_work_item_kind": {
      "limits": [
        {
          "counter": "set_work_item_kind_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 set_work_item_kind call is checked against it from then on.

FAQ

Questions about set_work_item_kind

What does the set_work_item_kind tool do? +

Set what KIND of work a card is: bug, story, or chore. This is a FIELD on the card, not a tag — it is orthogonal to urgency, so a card can be a bug AND Critical, and setting the kind never touches the tag (or the assignee, product, or body). Pass kind:null to clear it back to UNTYPED. Untyped is a real state and is NOT the same as "chore": a card nobody has categorised has no category, and recording chore would put a decision on the record that nobody made. If you do not know what a card is, leave it alone or clear it — do not guess. 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 set_work_item_kind accept? +

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

How do I enforce a policy on set_work_item_kind? +

Register the Starfield MCP server in PolicyLayer and add a rule for set_work_item_kind: 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 set_work_item_kind? +

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

Can I rate-limit set_work_item_kind? +

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

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

set_work_item_kind 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

emit_assumption_set on 0sec →set-prioity on Kanban MCP Server →team_manager_set_sources on Team Manager MCP → The MCP Attack Database →

Guides

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