AI agents use update_group_permission to create or update resources in Bitbucket — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Bitbucket environment.
This tool creates or modifies group permission records in Bitbucket. While it changes access control settings that could affect multiple users, the changes are reversible through subsequent updates or deletions. This makes it a Write operation rather than Destructive.
From the tool's definition Tool name is 'update_group_permission' with description 'Update or add a group'. The verbs 'update' and 'add' indicate modification of group data, which is reversible.
Attacks that exploit this kind of access
Update or add a group. It is categorised as a Write tool in the Bitbucket MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Bitbucket MCP server in PolicyLayer and add a rule for update_group_permission: 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 Bitbucket. Nothing to install.
update_group_permission 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_group_permission 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_group_permission. 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_group_permission is provided by the Bitbucket MCP server (javimaligno/mcp-server-bitbucket). 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 →