Search for code in a Bitbucket workspace or repository
AI agents call bb_search_code to retrieve information from Bitbucket Cloud MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search operation, which is a read-only action that retrieves and queries data without side effects. No data is created, modified, deleted, or executed. The search functionality poses minimal security risk as it only exposes existing code that the user would have access to view anyway through the Bitbucket API.
From the tool's definition Tool name 'bb_search_code' and description 'Search for code in a Bitbucket workspace or repository' indicates a query/retrieval operation with no modification or execution of code.
Attacks that exploit this kind of access
Search for code in a Bitbucket workspace or repository. It is categorised as a Read tool in the Bitbucket Cloud MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Bitbucket Cloud MCP Server MCP server in PolicyLayer and add a rule for bb_search_code: 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 Cloud MCP Server. Nothing to install.
bb_search_code 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 bb_search_code 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 bb_search_code. 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.
bb_search_code is provided by the Bitbucket Cloud MCP Server MCP server (or2ooo/bitbucket-mcp). 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 →