Mark all pending to-do items as done for the current authenticated user.
AI agents use gitlab_mark_all_todos_done 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 operation creates or modifies data reversibly within GitLab's todo system. The action is non-destructive (todos can be unmarked), affects only the authenticated user's own todos, and has minimal blast radius. Classified as Write rather than Read because it changes persistent state, and as low severity because marking todos as done has no impact on code, infrastructure, or project functionality.
From the tool's definition Tool description states 'Mark all pending to-do items as done for the current authenticated user' — this modifies state by changing todo item status from pending to done.
Documented attack patterns abuse exactly the kind of access gitlab_mark_all_todos_done 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 gitlab_mark_all_todos_done:
{
"version": "1",
"default": "deny",
"tools": {
"gitlab_mark_all_todos_done": {
"limits": [
{
"counter": "gitlab_mark_all_todos_done_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}gitlab_mark_all_todos_done 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.
Mark all pending to-do items as done for the current authenticated user. 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 gitlab_mark_all_todos_done: 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.
gitlab_mark_all_todos_done 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 gitlab_mark_all_todos_done 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 gitlab_mark_all_todos_done. 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.
gitlab_mark_all_todos_done is provided by the Gitlab MCP server (mcpland/gitlab-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Gitlab, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
190 Gitlab tools catalogued and risk-classified — across an index of 43,000+ MCP servers.