session_send · Claude Code MCP: Risk & Policy

WHAT IT DOES

What session_send does on Claude Code

AI agents invoke session_send to trigger actions in Claude Code. 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.

WHY IT NEEDS A POLICY

Why session_send needs a policy

Given the server context — controlling Claude Code sessions in tmux — 'session_send' almost certainly sends input/commands to an active tmux session, which constitutes executing arbitrary commands or code. The sibling tools (session_start, session_interrupt, session_destroy) reinforce that this server manages live interactive sessions.

From the tool's definition Tool name 'session_send' on a server that provides 'fine-grained control over interactive Claude Code sessions running inside tmux, enabling mid-session steering, interruption'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

session_send Rate-limited

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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "session_send": {
      "limits": [
        {
          "counter": "session_send_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Claude Code, so you can run agents against it safely.

FAQ

Questions about session_send

What does the session_send tool do? +

session_send. It is categorised as a Execute tool in the Claude Code MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on session_send? +

Register the Claude Code 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 Claude Code. Nothing to install.

What risk level is session_send? +

session_send is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit session_send? +

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.

How do I block session_send completely? +

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.

What MCP server provides session_send? +

session_send is provided by the Claude Code MCP server (joschi655/claude-code-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.