Paste clipboard content to one or more locations
AI agents use paste_lines to create or update resources in Cut-Copy-Paste Clipboard Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cut-Copy-Paste Clipboard Server environment.
paste_lines writes clipboard content into one or more file locations, which is a reversible write operation (supported by the undo_last_paste sibling tool). However, it has high severity because an AI agent could paste content into multiple files simultaneously, potentially overwriting or corrupting code across a codebase.
From the tool's definition 'Paste clipboard content to one or more locations' — writes/inserts content into files at specified locations
Attacks that exploit this kind of access
Paste clipboard content to one or more locations. It is categorised as a Write tool in the Cut-Copy-Paste Clipboard Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cut-Copy-Paste Clipboard Server MCP server in PolicyLayer and add a rule for paste_lines: 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 Cut-Copy-Paste Clipboard Server. Nothing to install.
paste_lines 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 paste_lines 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 paste_lines. 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.
paste_lines is provided by the Cut-Copy-Paste Clipboard Server MCP server (pr0j3c7t0dd-ltd/cut-copy-paste-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 →