High-risk tools in Code MCP Server
21 of the 73 tools in Code MCP Server are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
docker_buildExecuteBuild a Docker image from a Dockerfile
-
docker_composeExecuteManage Docker Compose services
-
docker_imagesExecuteManage Docker images (list, pull, push, remove, etc.)
-
docker_networksExecuteManage Docker networks
-
docker_runExecuteRun a Docker container
-
docker_systemExecuteDocker system operations and information
-
docker_volumesExecuteManage Docker volumes
-
git_pushExecutePush commits to remote
-
install_dependenciesExecuteInstall all project dependencies
-
npm_commandExecuteRun npm commands (install, test, build, etc)
-
pip_installExecuteInstall Python packages using pip
-
run_commandExecuteExecute a shell command
-
run_custom_toolExecuteExecute a custom tool defined in project configuration
-
run_javascriptExecuteExecute JavaScript code or script with Node.js
-
run_pythonExecuteExecute Python code or script
-
run_testsExecuteRun tests using appropriate test runner
-
secure_run_commandExecuteExecute a command with security restrictions (only allowed commands)
-
secure_run_command_sequenceExecuteExecute multiple commands in sequence with security restrictions
-
start_coding_sessionExecuteStart a new AI coding session with automatic change tracking
-
start_serverExecuteStart a development server
-
stop_serverExecuteStop a running server
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.