Medium Risk

send_keys

Send raw keystrokes to an agent's tmux pane. Use this to respond to interactive prompts (yes/no, numbered choices, permission approvals) displayed in an agent's terminal. By default appends Enter after the keys.

Part of the Taskflow server.

send_keys can modify Taskflow data, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE TASKFLOW →

Free to start. No card required.

AI agents use send_keys to create or modify resources in Taskflow. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call send_keys repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Taskflow.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "send_keys": {
      "limits": [
        {
          "counter": "send_keys_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full Taskflow policy for all 50 tools.

Get this rule live on your own Taskflow server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY TASKFLOW →

View all 50 tools →

These attack patterns abuse exactly the kind of access send_keys gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so send_keys only ever does what you allow.

SECURE TASKFLOW →

Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the send_keys tool do? +

Send raw keystrokes to an agent's tmux pane. Use this to respond to interactive prompts (yes/no, numbered choices, permission approvals) displayed in an agent's terminal. By default appends Enter after the keys.. It is categorised as a Write tool in the Taskflow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on send_keys? +

Register the Taskflow MCP server in PolicyLayer and add a rule for send_keys: 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 Taskflow. Nothing to install.

What risk level is send_keys? +

send_keys is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit send_keys? +

Yes. Add a rate_limit block to the send_keys 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 send_keys completely? +

Set action: deny in the PolicyLayer policy for send_keys. 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 send_keys? +

send_keys is provided by the Taskflow MCP server (@dalmasonto/taskflow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Taskflow tool call.

Deterministic rules across all 50 Taskflow tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.