AI agents call get_commit_statuses 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 queries and returns existing build/CI status data for a commit. It performs a read-only retrieval of information without creating, modifying, deleting, or executing any operations. The 'get' verb and lack of any action verbs (create, update, delete, run, execute) confirm it is a Read operation with minimal blast radius if misused.
From the tool's definition Tool name 'get_commit_statuses' and description 'Get build/CI statuses for a commit' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get build/CI statuses for a commit. 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 get_commit_statuses: 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.
get_commit_statuses 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 get_commit_statuses 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 get_commit_statuses. 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.
get_commit_statuses 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 →