download_attachments
AI agents call download_attachments to retrieve information from MCP Atlassian + Bitbucket without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Downloading attachments is a read operation that retrieves existing data without modification, deletion, or execution of code. While an attachment could theoretically contain malicious content, the tool itself performs no side effects—it only fetches data.
From the tool's definition Tool name 'download_attachments' indicates retrieval of attachment data. Sibling context shows similar retrieval operations (download_attachment, download_content_attachments, get_attachments) classified as data-fetching operations.
Attacks that exploit this kind of access
download_attachments. It is categorised as a Read tool in the MCP Atlassian + Bitbucket MCP Server, which means it retrieves data without modifying state.
Register the MCP Atlassian + Bitbucket MCP server in PolicyLayer and add a rule for download_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 + Bitbucket. Nothing to install.
download_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 download_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 download_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.
download_attachments is provided by the MCP Atlassian + Bitbucket MCP server (jellythomas/mcp-atlassian-with-bitbucket). 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 →