在 Azure DevOps 中建立新的 Work Item (例如 User Story, Bug, Task)。
AI agents use create_work_item to create or update resources in Azure Devops — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Azure Devops environment.
Creating a work item is a Write operation—it adds new data to the system but the action is reversible (the item can be deleted via delete_work_item, which exists as a sibling tool). While it modifies project state, it does not irreversibly destroy data or execute arbitrary code.
From the tool's definition Tool name 'create_work_item' and description indicates it creates new Work Items (User Story, Bug, Task) in Azure DevOps. The server description states it supports 'creating...work items'. This is a reversible creation operation.
Attacks that exploit this kind of access
在 Azure DevOps 中建立新的 Work Item (例如 User Story, Bug, Task)。. It is categorised as a Write tool in the Azure Devops MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Azure Devops MCP server in PolicyLayer and add a rule for create_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 Azure Devops. Nothing to install.
create_work_item is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_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 create_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.
create_work_item is provided by the Azure Devops MCP server (wuhuangjia/azure-devops-mcp-server). 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 →