AI agents call get_pr_details 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 appears to retrieve pull request details from Bitbucket without modifying any data. Even if it accesses sensitive information like PR metadata or reviewer comments, it performs no write, execute, or destructive operations. The 'get_' prefix and sibling patterns confirm read-only classification. Confidence is reduced slightly due to empty description, but contextual evidence is strong.
From the tool's definition Tool name 'get_pr_details' follows a 'get_' pattern indicating data retrieval with no modification. Server context shows this is part of a pull request review system where siblings include 'get_bitbucket_creds', 'get_bitbucket_pr_diff', and…
Attacks that exploit this kind of access
get_pr_details. 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_details: 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_details 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_details 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_details. 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_details is provided by the Bitbucket MCP server (jishadmt/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 →