AI agents call get_pr 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 pull request information without creating, modifying, or deleting data. It is a simple query operation that reads existing data from Bitbucket, consistent with the 'Read' category for fetch operations. The blast radius is minimal—worst case, an agent reads PR details it shouldn't have access to, which is a data exposure risk rather than a destructive or system-altering one.
From the tool's definition Tool name 'get_pr' and description 'Fetch a Bitbucket pull request' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Fetch a Bitbucket pull request. 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_pr: 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_pr 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_pr 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_pr. 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_pr 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 →