Unsubscribe from watching a pull request.
AI agents call unwatch_pull_request to retrieve information from Bitbucket Server MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool manages notification preferences rather than manipulating repository data. Unwatching a pull request is a read-side operation that adjusts subscription state without side effects on code, commits, or pull request content. The blast radius is minimal—a misuse would only affect the user's notification settings, not data integrity or system state.
From the tool's definition Tool performs 'Unsubscribe from watching a pull request' - a preference/notification operation with no data creation, modification, or deletion. The action is reversible (user can re-subscribe by watching again).
Attacks that exploit this kind of access
Unsubscribe from watching a pull request. It is categorised as a Read tool in the Bitbucket Server MCP MCP Server, which means it retrieves data without modifying state.
Register the Bitbucket Server MCP server in PolicyLayer and add a rule for unwatch_pull_request: 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 Server MCP. Nothing to install.
unwatch_pull_request 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 unwatch_pull_request 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 unwatch_pull_request. 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.
unwatch_pull_request is provided by the Bitbucket Server MCP server (manpreetshuann/bitbucket-server-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 →