Add a command to the blacklist. Once blocked, the command cannot be executed until unblocked.
AI agents use block_command to create or update resources in Desktop Commander MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Desktop Commander MCP environment.
This tool modifies a configuration list (the command blacklist) in a reversible way — commands can be unblocked later. It creates/updates a security policy entry rather than deleting data, executing code, or moving money. Misuse could disrupt legitimate operations by blocking critical commands, hence medium severity.
From the tool's definition Add a command to the blacklist. Once blocked, the command cannot be executed until unblocked.
Documented attack patterns abuse exactly the kind of access block_command gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Desktop Commander MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for block_command:
{
"version": "1",
"default": "deny",
"tools": {
"block_command": {
"limits": [
{
"counter": "block_command_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}block_command stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Add a command to the blacklist. Once blocked, the command cannot be executed until unblocked. It is categorised as a Write tool in the Desktop Commander MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Desktop Commander MCP server in PolicyLayer and add a rule for block_command: 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 Desktop Commander MCP. Nothing to install.
block_command is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the block_command 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 block_command. 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.
block_command is provided by the Desktop Commander MCP server (mrgnss/claudedesktopcommander). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Desktop Commander MCP, 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.
19 Desktop Commander MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.