Gets a structured line-by-line diff for a specific file in a pull request. Returns JSON with hunks, segments, and exact line numbers (source and destination). Includes existing comments embedded in the diff. Whitespace changes are always included. This is essential for commenting on specific line...
AI agents call get_pull_request_file_diff to retrieve information from Mcp Bitbucket Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries pull request file diff data, returning structured information about code changes. It has no side effects, does not modify any data, and only fetches existing information. It is a straightforward Read operation. The severity is low because accessing diff data poses minimal security risk even if misused by an AI agent.
From the tool's definition Tool name 'get_pull_request_file_diff' and description state it 'Gets a structured line-by-line diff' and 'Returns JSON' - purely retrieval operations with no modification, creation, deletion, or execution of code.
Attacks that exploit this kind of access
Gets a structured line-by-line diff for a specific file in a pull request. Returns JSON with hunks, segments, and exact line numbers (source and destination). Includes existing comments embedded in the diff. Whitespace changes are always included. This is essential for commenting on specific lines - use the line numbers from this response when adding comments. It is categorised as a Read tool in the Mcp Bitbucket Server MCP Server, which means it retrieves data without modifying state.
Register the Mcp Bitbucket Server MCP server in PolicyLayer and add a rule for get_pull_request_file_diff: 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 Mcp Bitbucket Server. Nothing to install.
get_pull_request_file_diff 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_pull_request_file_diff 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_pull_request_file_diff. 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_pull_request_file_diff is provided by the Mcp Bitbucket Server MCP server (mcp-bitbucket-server). 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 →