Send the same text + Enter to SPECIFIC surfaces (not all). Target by surface refs — useful when only some agents need the same instruction.
AI agents invoke cmux_send_submit_some to trigger actions in Cmux Agent. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool sends text and simulates pressing Enter on specific terminal or browser surfaces, which executes commands or instructions in those sessions. The effect depends entirely on what text is sent, and could trigger any operation in the targeted AI CLI sessions or browser instances. Ranked Execute (not Write) because it triggers arbitrary operations in external sessions rather than simply writing data.
From the tool's definition 'Send the same text + Enter to SPECIFIC surfaces' — sends input and submits it to targeted terminal/browser panes, triggering execution of whatever command or instruction is sent
Documented attack patterns abuse exactly the kind of access cmux_send_submit_some gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cmux Agent, and nothing reaches the server without passing your rules. This is the rule we recommend for cmux_send_submit_some:
{
"version": "1",
"default": "deny",
"tools": {
"cmux_send_submit_some": {
"limits": [
{
"counter": "cmux_send_submit_some_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}cmux_send_submit_some stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Send the same text + Enter to SPECIFIC surfaces (not all). Target by surface refs — useful when only some agents need the same instruction. It is categorised as a Execute tool in the Cmux Agent MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cmux Agent MCP server in PolicyLayer and add a rule for cmux_send_submit_some: 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 Cmux Agent. Nothing to install.
cmux_send_submit_some is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the cmux_send_submit_some 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 cmux_send_submit_some. 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.
cmux_send_submit_some is provided by the Cmux Agent MCP server (multiagentcognition/cmux-agent-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Cmux Agent, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
63 Cmux Agent tools catalogued and risk-classified — across an index of 43,000+ MCP servers.