AI agents use update_repository 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 repository configuration attributes in a reversible manner. While these changes could have cascading effects (visibility changes affect access control, name changes may break integrations), they do not permanently destroy data nor move financial resources. The blast radius is medium because misconfiguration could disrupt repository access or break CI/CD pipelines, but changes can be undone.
From the tool's definition Tool name is 'update_repository' and description states it updates repository settings (project, visibility, description, name) — classic reversible modification of metadata without deletion or destruction.
Attacks that exploit this kind of access
Update repository settings (project, visibility, description, name). 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_repository: 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_repository 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_repository 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_repository. 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_repository 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 →