AI agents use approvePullRequest to create or update resources in Bitbucket MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Bitbucket MCP environment.
Approving a pull request is a write operation that changes the approval state of a PR, which is reversible (an approval can be withdrawn). While it may have workflow implications (e.g., enabling merging), the tool itself performs a data modification rather than deletion, execution, or financial action.
From the tool's definition The tool "approvePullRequest" modifies the state of a pull request by adding an approval, which is a reversible change to repository metadata. This is a write operation that changes data (approval status) but does not destroy or execute arbitrary code.
Documented attack patterns abuse exactly the kind of access approvePullRequest gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Bitbucket MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for approvePullRequest:
{
"version": "1",
"default": "deny",
"tools": {
"approvePullRequest": {
"limits": [
{
"counter": "approvepullrequest_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}approvePullRequest stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Approve a pull request. It is categorised as a Write tool in the Bitbucket MCP 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 approvePullRequest: 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. Nothing to install.
approvePullRequest 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 approvePullRequest 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 approvePullRequest. 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.
approvePullRequest is provided by the Bitbucket MCP server (matanyemini/bitbucket-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Bitbucket MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
49 Bitbucket MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.