Send text and keystrokes to a terminal. Always pass as array. Examples: [
AI agents invoke mcpretentious-type to trigger actions in MCPretentious. 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 keystrokes to a terminal is effectively arbitrary command execution. An AI agent could type any shell command (rm -rf, curl | bash, etc.) into the terminal, making this a critical-severity Execute tool. The blast radius is maximal since terminal access is unrestricted.
From the tool's definition 'Send text and keystrokes to a terminal' — this tool injects arbitrary input into a terminal session, enabling execution of any shell command or keystroke sequence.
Documented attack patterns abuse exactly the kind of access mcpretentious-type gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCPretentious, and nothing reaches the server without passing your rules. This is the rule we recommend for mcpretentious-type:
{
"version": "1",
"default": "deny",
"tools": {
"mcpretentious-type": {
"limits": [
{
"counter": "mcpretentious-type_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}mcpretentious-type 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 text and keystrokes to a terminal. Always pass as array. Examples: [. It is categorised as a Execute tool in the MCPretentious MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCPretentious MCP server in PolicyLayer and add a rule for mcpretentious-type: 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 MCPretentious. Nothing to install.
mcpretentious-type 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 mcpretentious-type 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 mcpretentious-type. 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.
mcpretentious-type is provided by the MCPretentious MCP server (oetiker/mcpretentious). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCPretentious, 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 MCPretentious tools catalogued and risk-classified — across an index of 43,000+ MCP servers.