AI agents invoke send_keys to trigger actions in Nvim. 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 running Neovim session is an Execute-class action — it can trigger arbitrary editor commands, run shell commands via ':!', write files, or cause other side effects depending on what keys are sent. The server is explicitly described as enabling command execution.
From the tool's definition Tool name 'send_keys' on a server that 'control[s] running Neovim sessions via RPC socket, supporting command execution'. Empty description lowers confidence.
Documented attack patterns abuse exactly the kind of access send_keys gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Nvim, and nothing reaches the server without passing your rules. This is the rule we recommend for send_keys:
{
"version": "1",
"default": "deny",
"tools": {
"send_keys": {
"limits": [
{
"counter": "send_keys_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}send_keys 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_keys. It is categorised as a Execute tool in the Nvim MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Nvim 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 Nvim. Nothing to install.
send_keys 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 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.
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.
send_keys is provided by the Nvim MCP server (paulburgess1357/nvim-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 17 Nvim tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
17 Nvim tools catalogued and risk-classified — across an index of 42,500+ MCP servers.