AI agents use declinePullRequest 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.
Declining a pull request changes its state from open to declined, which is a reversible action (the PR can be reopened or recreated). It modifies data in the repository but does not delete or destroy anything permanently, making it a Write operation. Misuse could block legitimate code contributions, hence medium severity.
From the tool's definition Decline a pull request
Documented attack patterns abuse exactly the kind of access declinePullRequest 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 declinePullRequest:
{
"version": "1",
"default": "deny",
"tools": {
"declinePullRequest": {
"limits": [
{
"counter": "declinepullrequest_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} declinePullRequest 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.
Decline 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 declinePullRequest: 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.
declinePullRequest 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 declinePullRequest 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 declinePullRequest. 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.
declinePullRequest 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.