AI agents call get_pipeline_step_log 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 retrieves and reads pipeline logs, which is a read-only query operation. It does not create, modify, delete, or execute any actions. The blast radius of misuse is minimal—an attacker could only view logs they query for, which does not compromise system integrity or enable further attacks beyond information disclosure.
From the tool's definition Tool description states 'Fetch the log output of a specific pipeline step' — this is a retrieval operation with no side effects. The parameters (pipeline_uuid, step_uuid) are identifiers for querying existing data, not modifying or executing operations.
Attacks that exploit this kind of access
Fetch the log output of a specific pipeline step. Use pipeline_uuid and step_uuid from. 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_pipeline_step_log: 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_pipeline_step_log 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_pipeline_step_log 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_pipeline_step_log. 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_pipeline_step_log is provided by the Bitbucket MCP server (jacobpixleratgather/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 →