Publish all pending comments for a pull request
AI agents use publishPendingComments 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.
This tool modifies data by converting pending (hidden) comments into published (visible) comments on a pull request. While technically reversible through deletion, publishing is a content modification action that affects the PR's collaborative record. It does not retrieve data (Read), execute arbitrary code (Execute), permanently delete data (Destructive), or involve financial transactions (Financial).
From the tool's definition Tool description states 'Publish all pending comments for a pull request' — this action creates/makes visible comments that were previously in draft/pending state, modifying the PR's comment state irreversibly in terms of visibility.
Documented attack patterns abuse exactly the kind of access publishPendingComments 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 publishPendingComments:
{
"version": "1",
"default": "deny",
"tools": {
"publishPendingComments": {
"limits": [
{
"counter": "publishpendingcomments_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}publishPendingComments 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.
Publish all pending comments for 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 publishPendingComments: 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.
publishPendingComments 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 publishPendingComments 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 publishPendingComments. 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.
publishPendingComments 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.