Send text to the clipstream buffer.
AI agents use clip to create or update resources in Mcp Clipstream — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Clipstream environment.
This tool writes data to a clipboard buffer, which is a reversible operation with minimal blast radius. It does not execute code, delete data, or move money. The worst-case misuse would be polluting the clipboard with unwanted text, which is easily recoverable and low-severity.
From the tool's definition Tool description states 'Send text to the clipstream buffer' — a write operation that creates/modifies data in a clipboard buffer. The sibling tool names (clip_cmd, clip_code, clip_table) confirm this is about capturing and storing text data.
Attacks that exploit this kind of access
Send text to the clipstream buffer. It is categorised as a Write tool in the Mcp Clipstream MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Clipstream MCP server in PolicyLayer and add a rule for clip: 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 Clipstream. Nothing to install.
clip 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 clip 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 clip. 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.
clip is provided by the Mcp Clipstream MCP server (shamis6ali/mcp-clipstream). 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 →