get_page_history
AI agents call get_page_history to retrieve information from MCP Atlassian without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'get_page_history' follows the Read category pattern (get = retrieval). It accesses historical version information about Confluence pages, which is a non-destructive query operation. No side effects, modifications, code execution, or financial operations are implied.
From the tool's definition Tool name is 'get_page_history' which uses the 'get' verb, a retrieval pattern. The description is empty, but the name strongly indicates it fetches historical page data from Confluence without modification.
Attacks that exploit this kind of access
get_page_history. It is categorised as a Read tool in the MCP Atlassian MCP Server, which means it retrieves data without modifying state.
Register the MCP Atlassian MCP server in PolicyLayer and add a rule for get_page_history: 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.
get_page_history 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 get_page_history 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 get_page_history. 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.
get_page_history is provided by the MCP Atlassian MCP server (sooperset/mcp-atlassian). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.