Add an attachment to a card using a URL
AI agents use add_attachment to create or update resources in Mochi MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mochi MCP Server environment.
The tool creates/modifies data by attaching a URL-based resource to a card, which is a reversible operation. It does not delete data (would be Destructive), execute arbitrary code (would be Execute), or move money (would be Financial).
From the tool's definition Tool description states 'Add an attachment to a card using a URL', which creates new data (an attachment) associated with an existing card.
Attacks that exploit this kind of access
Add an attachment to a card using a URL. It is categorised as a Write tool in the Mochi MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mochi MCP Server MCP server in PolicyLayer and add a rule for add_attachment: 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 Mochi MCP Server. Nothing to install.
add_attachment 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 add_attachment 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 add_attachment. 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.
add_attachment is provided by the Mochi MCP Server MCP server (shunkus/mochi-mcp-server). 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 →