get_work_item
Read one card by id: title, body, product, assignee, reporter, creator, its stored tag, and how long it has been in its current column. THREE DIFFERENT PEOPLE can appear on a card and they answer different questions: assignee is who is doing it (and changes hands over the card's life), reporterPe...
This record as markdown: /tools/adrata-starfield-mcp/get-work-item.md
What get_work_item does on Starfield
AI agents call get_work_item to retrieve information from Starfield without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
itemId | string | Yes | Card id. |
Parameters from the server's own tool schema.
Why get_work_item is rated Low
Even though get_work_item only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs get_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 get_work_item, this is the rule to start with:
get_work_item is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Starfield, apply this rule, and every get_work_item call is checked against it from then on.
Questions about get_work_item
Read one card by id: title, body, product, assignee, reporter, creator, its stored tag, and how long it has been in its current column. THREE DIFFERENT PEOPLE can appear on a card and they answer different questions: assignee is who is doing it (and changes hands over the card's life), reporterPersonId is the customer who asked (only on a card ingested from email), and createdBy is the teammate who wrote the card — resolved to a name, never changing, and the person to ask what the card meant. An absent createdBy means the card predates creator tracking, not that nobody made it. It is categorised as a Read tool in the Starfield MCP Server, which means it retrieves data without modifying state.
get_work_item accepts 1 parameter: itemId. Required: itemId. The full parameter table on this page comes from the server's own tool schema.
Register the Starfield MCP server in PolicyLayer and add a rule for get_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.
get_work_item is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_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.
Set action: deny in the PolicyLayer policy for get_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.
get_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.
More on Starfield, and thousands of servers like it.
This server
Across the catalogue