omg_clear_state
Clear state for a given OMG mode or all modes
This record as markdown: /tools/io-github-zereight-gitlab-mcp/omg-clear-state.md
What omg_clear_state does on Gitlab Mcp
AI agents call omg_clear_state to permanently remove resources in Gitlab Mcp, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why omg_clear_state is rated Critical
State clearing operations irreversibly remove data and cannot be undone. While the exact scope is unclear (OMG mode context not defined in the provided description), the capability to clear state for multiple modes at once presents significant risk of unintended data loss if an AI agent misuses this tool with incorrect parameters.
From the tool's definition Tool name 'omg_clear_state' with description 'Clear state for a given OMG mode or all modes' indicates irreversible state deletion.
Attacks that exploit this kind of access
The rule that runs omg_clear_state safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Gitlab Mcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For omg_clear_state, this is the rule to start with:
omg_clear_state is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Gitlab Mcp, apply this rule, and every omg_clear_state call is checked against it from then on.
Questions about omg_clear_state
Clear state for a given OMG mode or all modes. It is categorised as a Destructive tool in the Gitlab Mcp MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Gitlab MCP server in PolicyLayer and add a rule for omg_clear_state: 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 Mcp. Nothing to install.
omg_clear_state is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the omg_clear_state 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 omg_clear_state. 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.
omg_clear_state is provided by the Gitlab MCP server (@zereight/mcp-gitlab). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Gitlab, and thousands of servers like it.
Across the catalogue