AI agents use confluence_update_page to create or update resources in MCP Atlassian — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Atlassian environment.
The tool updates/modifies Confluence pages, which is a Write operation—data is changed but the action is reversible (prior versions typically exist in Confluence's history). This is not Destructive (no permanent deletion), not Execute (no code execution), not Financial.
From the tool's definition Tool name 'confluence_update_page' indicates modification of existing Confluence page content. Sibling tools include 'confluence_create_page' (Write) and 'get_confluence_content' (Read), establishing the pattern that tools named with 'update' or 'create' in…
Documented attack patterns abuse exactly the kind of access confluence_update_page gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Atlassian, and nothing reaches the server without passing your rules. This is the rule we recommend for confluence_update_page:
{
"version": "1",
"default": "deny",
"tools": {
"confluence_update_page": {
"limits": [
{
"counter": "confluence_update_page_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}confluence_update_page 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.
confluence_update_page. It is categorised as a Write tool in the MCP Atlassian MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Atlassian MCP server in PolicyLayer and add a rule for confluence_update_page: 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 MCP Atlassian. Nothing to install.
confluence_update_page 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 confluence_update_page 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 confluence_update_page. 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.
confluence_update_page is provided by the MCP Atlassian MCP server (samwang0723/mcp-atlassian). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Atlassian, 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.
20 MCP Atlassian tools catalogued and risk-classified — across an index of 43,000+ MCP servers.