Retrieves detailed information about one or multiple work items. Use this tool when you need to: - View the complete details of a specific work item - Examine the current state, assigned user, and other properties - Get information about multiple work items at once - Access the full description a...
AI agents call get_work_item to retrieve information from MCP Azure DevOps Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a pure data retrieval operation with no side effects. It queries and returns work item information without creating, modifying, or deleting any data. The blast radius of misuse is minimal—an agent could retrieve unauthorized information but cannot alter system state. This clearly fits the 'Read' category.
From the tool's definition Tool description states it 'Retrieves detailed information about one or multiple work items' and 'View the complete details of a specific work item' with no mention of modification, creation, or deletion.
Documented attack patterns abuse exactly the kind of access get_work_item gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Azure DevOps Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_work_item:
{
"version": "1",
"default": "deny",
"tools": {
"get_work_item": {}
}
}get_work_item is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Retrieves detailed information about one or multiple work items. Use this tool when you need to: - View the complete details of a specific work item - Examine the current state, assigned user, and other properties - Get information about multiple work items at once - Access the full description and custom fields of work items Args: id: The work item ID or a list of work item IDs Returns: Formatted string containing comprehensive information for the requested work item(s), including all system and custom fields, formatted as markdown with clear section headings. It is categorised as a Read tool in the MCP Azure DevOps Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Azure DevOps Server 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 MCP Azure DevOps Server. 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 MCP Azure DevOps Server MCP server (vortiago/mcp-azure-devops). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 21 MCP Azure DevOps Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
21 MCP Azure DevOps Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.