get_workitem
AI agents call get_workitem to retrieve information from PolarionMcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name and naming pattern ('get_*') indicate this retrieves or queries work item data from a Polarion ALM system. No side effects are implied. While the description is empty (lowering confidence slightly), the tool's semantic purpose and context among other read-only discovery/retrieval tools make it clearly a Read operation.
From the tool's definition Tool name 'get_workitem' and its position among sibling tools (discover_work_item_types, get_document, get_documents, get_named_queries, get_plan, get_plans, get_project_info) that are all Read operations.
Attacks that exploit this kind of access
get_workitem. It is categorised as a Read tool in the PolarionMcp MCP Server, which means it retrieves data without modifying state.
Register the Polarion MCP server in PolicyLayer and add a rule for get_workitem: 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 PolarionMcp. Nothing to install.
get_workitem 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_workitem 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_workitem. 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_workitem is provided by the Polarion MCP server (mmerah/polarionmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →