AI agents call list_repositories to retrieve information from Bitbucket without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation to enumerate and search repositories. It has no side effects, does not execute code or commands, does not modify or delete data, and does not involve financial operations. The blast radius of misuse is minimal—an agent could only discover what repositories exist in the workspace, which is typically low-sensitivity information and often already visible to authenticated users.
From the tool's definition Tool name 'list_repositories' and description 'List and search repositories in the workspace' indicate a query operation that retrieves repository metadata without modifying, executing, or deleting data.
Attacks that exploit this kind of access
List and search repositories in the workspace. It is categorised as a Read tool in the Bitbucket MCP Server, which means it retrieves data without modifying state.
Register the Bitbucket MCP server in PolicyLayer and add a rule for list_repositories: 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.
list_repositories is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_repositories 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 list_repositories. 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.
list_repositories 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 →