get_attachments
AI agents call get_attachments 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 'get_' prefix is a strong indicator of read-only operation. Retrieving attachments from Confluence or Jira pages/issues does not modify, execute code, or delete data. It has minimal blast radius—worst case being unauthorized access to documents already in the system. Confidence is slightly reduced due to empty description, but sibling tool patterns provide sufficient context.
From the tool's definition Tool name 'get_attachments' indicates retrieval of attachment data. The description is empty, but the pattern 'get_*' among sibling tools (get_activities, get_agile_boards, get_all_projects, get_board_issues) consistently represents read operations.
Attacks that exploit this kind of access
get_attachments. 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_attachments: 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_attachments 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_attachments 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_attachments. 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_attachments is provided by the Mcp Atlassian MCP server (voarsh2/mcp-atlassian). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →