AI agents use update_issue to create or update resources in Gitlab — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gitlab environment.
This tool creates or modifies data reversibly. Updates to issues (title, description, status, assignees, labels) can be reverted or corrected, so it does not meet the Destructive threshold. It is not a Read operation (which retrieves data without changes), not Execute (which runs arbitrary code), not Financial, and not Other.
From the tool's definition Tool name is 'update_issue' and description states 'Update an existing issue', which modifies existing data (issue content, state, assignments, labels, etc.) in a reversible manner.
Documented attack patterns abuse exactly the kind of access update_issue gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Gitlab, and nothing reaches the server without passing your rules. This is the rule we recommend for update_issue:
{
"version": "1",
"default": "deny",
"tools": {
"update_issue": {
"limits": [
{
"counter": "update_issue_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_issue stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Update an existing issue. It is categorised as a Write tool in the Gitlab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gitlab MCP server in PolicyLayer and add a rule for update_issue: 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 Gitlab. Nothing to install.
update_issue 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 update_issue 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 update_issue. 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.
update_issue is provided by the Gitlab MCP server (yoda-digital/mcp-gitlab-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 88 Gitlab tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
88 Gitlab tools catalogued and risk-classified — across an index of 42,500+ MCP servers.