Send a message to an active (running) session
AI agents invoke session_send to trigger actions in Climux. 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.
Sending messages to an active coding CLI session can cause the agent to execute arbitrary code, run shell commands, modify files, or perform other high-impact operations. The blast radius is high because the content of the message determines what actions are taken, and the server is explicitly described as orchestrating 'multiple coding CLI tools' for AI agents.
From the tool's definition "Send a message to an active (running) session" — dispatches input to a live CLI coding agent session, triggering arbitrary command execution depending on message content
Documented attack patterns abuse exactly the kind of access session_send gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Climux, and nothing reaches the server without passing your rules. This is the rule we recommend for session_send:
{
"version": "1",
"default": "deny",
"tools": {
"session_send": {
"limits": [
{
"counter": "session_send_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}session_send 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 a message to an active (running) session. It is categorised as a Execute tool in the Climux MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Climux MCP server in PolicyLayer and add a rule for session_send: 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 Climux. Nothing to install.
session_send 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 session_send 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 session_send. 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.
session_send is provided by the Climux MCP server (veithly/climux). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Climux, 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.
9 Climux tools catalogued and risk-classified — across an index of 43,000+ MCP servers.