List all commits that are part of a pull request
AI agents call list_pr_commits to retrieve information from Bitbucket MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves commit information associated with a pull request. It does not modify, delete, execute code, or trigger external operations. The action is purely informational and read-only, consistent with the Read category. Blast radius is minimal—misuse would only expose commit metadata already accessible through the pull request.
From the tool's definition Tool name 'list_pr_commits' and description 'List all commits that are part of a pull request' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
List all commits that are part of a pull request. It is categorised as a Read tool in the Bitbucket MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Bitbucket MCP Server MCP server in PolicyLayer and add a rule for list_pr_commits: 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 MCP Server. Nothing to install.
list_pr_commits 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 list_pr_commits 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 list_pr_commits. 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.
list_pr_commits is provided by the Bitbucket MCP Server MCP server (zhanglc/bitbucket-mcp-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 →