AI agents invoke make_build to trigger actions in MCP DevTools 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.
The tool triggers execution of arbitrary build commands via the make system. While not destructive by itself, build commands can have significant side effects: they compile code, generate artifacts, consume disk/CPU resources, and may invoke nested scripts with unpredictable effects. An AI agent misusing this (e.g., in a loop, or on an untrusted Makefile) could exhaust resources or trigger unintended operations.
From the tool's definition Tool description states 'Run make build command' — this executes an external build system command whose side effects (compilation, artifact generation, resource usage) depend on the project's Makefile and build scripts.
Documented attack patterns abuse exactly the kind of access make_build gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP DevTools Server, and nothing reaches the server without passing your rules. This is the rule we recommend for make_build:
{
"version": "1",
"default": "deny",
"tools": {
"make_build": {
"limits": [
{
"counter": "make_build_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}make_build 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.
Run make build command to build the project. It is categorised as a Execute tool in the MCP DevTools Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP DevTools Server MCP server in PolicyLayer and add a rule for make_build: 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 MCP DevTools Server. Nothing to install.
make_build 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 make_build 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 make_build. 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.
make_build is provided by the MCP DevTools Server MCP server (rshade/mcp-devtools-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP DevTools Server, 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.
79 MCP DevTools Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.