mcp_write
AI agents use mcp_write to create or update resources in MCP CopyQ Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP CopyQ Server environment.
This tool creates or modifies clipboard data reversibly. Writing to clipboard is a side effect but not destructive (data can be overwritten or cleared) and not irreversible. The medium severity reflects that clipboard manipulation could leak sensitive data or interfere with user workflows, but lacks the blast radius of code execution or financial impact.
From the tool's definition Tool named 'mcp_write' on a server described as enabling 'writing...clipboard items.' The empty description limits certainty, but the name and server context clearly indicate write operations to clipboard data.
Attacks that exploit this kind of access
mcp_write. It is categorised as a Write tool in the MCP CopyQ Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP CopyQ Server MCP server in PolicyLayer and add a rule for mcp_write: 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 CopyQ Server. Nothing to install.
mcp_write 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 mcp_write 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 mcp_write. 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.
mcp_write is provided by the MCP CopyQ Server MCP server (list91/mcp-copyq). 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 →