AI agents use update_user_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 modifies user permissions and user data, which is a reversible Write operation. However, it affects access control, which has significant blast radius if misused by an AI agent to grant inappropriate permissions to users or modify critical account settings. The high severity reflects that permission changes can affect system security and user access across repositories and pipelines.
From the tool's definition Tool name 'update_user_permission' and description 'Update or add a user' indicate modification of user access permissions and user records.
Attacks that exploit this kind of access
Update or add a user. 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_user_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_user_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_user_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_user_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_user_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 →