Resolve the WorkItem global ID (gid://gitlab/WorkItem/N) for an epic or issue. Required as parent_work_item_id / child_work_item_ids on link_work_items and unlink_work_items.
AI agents call get_work_item_id to retrieve information from Mcp Gitlab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a retrieval operation with no side effects. It queries GitLab to fetch an identifier, analogous to a search or get operation. While it supports downstream operations (link/unlink), the tool itself performs no modifications, executions, or destructive actions. The blast radius of misuse is minimal—an attacker could retrieve IDs, but cannot act on them without invoking separate tools.
From the tool's definition Tool resolves and retrieves a WorkItem global ID without modifying, deleting, or executing operations. Description states it 'Resolve[s] the WorkItem global ID' and is 'Required as parent_work_item_id / child_work_item_ids on link_work_items and…
Attacks that exploit this kind of access
Resolve the WorkItem global ID (gid://gitlab/WorkItem/N) for an epic or issue. Required as parent_work_item_id / child_work_item_ids on link_work_items and unlink_work_items. It is categorised as a Read tool in the Mcp Gitlab MCP Server, which means it retrieves data without modifying state.
Register the Mcp Gitlab MCP server in PolicyLayer and add a rule for get_work_item_id: 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 Gitlab. Nothing to install.
get_work_item_id 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_id 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_id. 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_id is provided by the Mcp Gitlab MCP server (wanadev/gitlab-mcp). 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 →