AI agents call jira_download_all_attachments to retrieve information from Jira Dev without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool downloads (retrieves) attachments without modifying, deleting, or executing any operations. It simply fetches existing data from Jira issues. The MIME type filtering is a read-side parameter for querying, not a modification. This is a classic Read category tool with low severity since attachment downloads do not alter system state.
From the tool's definition Tool description states 'Download all attachments from a Jira issue' - this is a retrieval operation with no side effects.
Attacks that exploit this kind of access
Download all attachments from a Jira issue in a single call. Optionally filter by MIME type (e.g. It is categorised as a Read tool in the Jira Dev MCP Server, which means it retrieves data without modifying state.
Register the Jira Dev MCP server in PolicyLayer and add a rule for jira_download_all_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 Jira Dev. Nothing to install.
jira_download_all_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 jira_download_all_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 jira_download_all_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.
jira_download_all_attachments is provided by the Jira Dev MCP server (jira-dev-mcp). 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 →