Run a whitelisted system command. Free-form: uptime, hostname, df, free, top, ps, who, date, uname, lsblk, lscpu, lsmem, vcgencmd. Restricted to read-only subcommands: git (status/log/diff/show/rev-parse/describe/ls-files/ls-tree/blame/shortlog/reflog/branch), gh (pr/issue/run/repo/release/workfl...
AI agents invoke run_command to trigger actions in Multi-Tool MCP Server. 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.
Despite restrictions to 'read-only' and 'whitelisted' commands, this tool triggers execution of arbitrary system commands and external processes. The blocking of shell metacharacters limits but does not eliminate Execute risk—an agent could still chain commands through whitelisted tools or exploit edge cases in command filtering.
From the tool's definition Tool description states 'Run a whitelisted system command' with capability to execute commands like uptime, hostname, df, free, top, ps, who, date, uname, lsblk, lscpu, lsmem, vcgencmd, and restricted git/gh commands.
Attacks that exploit this kind of access
Run a whitelisted system command. Free-form: uptime, hostname, df, free, top, ps, who, date, uname, lsblk, lscpu, lsmem, vcgencmd. Restricted to read-only subcommands: git (status/log/diff/show/rev-parse/describe/ls-files/ls-tree/blame/shortlog/reflog/branch), gh (pr/issue/run/repo/release/workflow/auth — read-only actions only). Shell metacharacters (;, &, |, <, >,. It is categorised as a Execute tool in the Multi-Tool MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Multi-Tool MCP Server MCP server in PolicyLayer and add a rule for run_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 Multi-Tool MCP Server. Nothing to install.
run_command 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 run_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 run_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.
run_command is provided by the Multi-Tool MCP Server MCP server (shawn-falconbury/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
run_command is one line of Multi-Tool MCP Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →