AI agents use resolve_pr_comment to create or update resources in Bitbucket — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Bitbucket environment.
This tool creates or modifies data reversibly by changing the resolution status of a PR comment. It does not execute code, delete data, or perform financial operations. The action is reversible (comments can be marked as resolved or unresolved again), placing it in the Write category. Severity is low because the blast radius of misuse is limited to PR comment metadata with no impact on code, builds, or deployments.
From the tool's definition Tool description states: 'Mark a PR comment as resolved or unresolved.' This modifies the state of a PR comment (resolved/unresolved status) reversibly.
Attacks that exploit this kind of access
Mark a PR comment as resolved or unresolved. Defaults to resolved=true. Use. It is categorised as a Write tool in the Bitbucket MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Bitbucket MCP server in PolicyLayer and add a rule for resolve_pr_comment: 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.
resolve_pr_comment is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the resolve_pr_comment 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 resolve_pr_comment. 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.
resolve_pr_comment 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 →