Execute a shell command in repository context.
AI agents invoke execute_shell_command to trigger actions in CodeGraphMCPServer. 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.
Shell command execution is inherently Execute category—it triggers external operations (compilation, scripts, system calls) whose consequences depend entirely on user-supplied arguments. In a code analysis context, this creates critical risk: an AI agent could run destructive commands (rm -rf), exfiltrate data, modify files, or compromise the repository.
From the tool's definition Tool is explicitly named "execute_shell_command" and described as "Execute a shell command in repository context." This directly invokes arbitrary shell commands with effects dependent on the command arguments.
Documented attack patterns abuse exactly the kind of access execute_shell_command gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CodeGraphMCPServer, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_shell_command:
{
"version": "1",
"default": "deny",
"tools": {
"execute_shell_command": {
"limits": [
{
"counter": "execute_shell_command_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_shell_command 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.
Execute a shell command in repository context. It is categorised as a Execute tool in the CodeGraphMCPServer MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the CodeGraphMCPServer MCP server in PolicyLayer and add a rule for execute_shell_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 CodeGraphMCPServer. Nothing to install.
execute_shell_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 execute_shell_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 execute_shell_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.
execute_shell_command is provided by the CodeGraphMCPServer MCP server (nahisaho/codegraphmcpserver). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from CodeGraphMCPServer, 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.
14 CodeGraphMCPServer tools catalogued and risk-classified — across an index of 43,000+ MCP servers.