AI agents invoke api to trigger actions in Make. 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.
Because the tool allows arbitrary GitHub API calls, it is not limited to read-only operations. An AI agent could use it to create/delete repositories, modify code, manage webhooks, or perform other high-impact actions. The 'arbitrary' nature means the worst-case severity applies, placing it in Execute (covering a broad range of side-effecting operations).
From the tool's definition 'Makes arbitrary GitHub API calls via' — the tool executes arbitrary GitHub API calls, which can span read, write, and destructive operations depending on the endpoint and HTTP method used.
Documented attack patterns abuse exactly the kind of access api gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Make, and nothing reaches the server without passing your rules. This is the rule we recommend for api:
{
"version": "1",
"default": "deny",
"tools": {
"api": {
"limits": [
{
"counter": "api_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}api 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.
Makes arbitrary GitHub API calls via. It is categorised as a Execute tool in the Make MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Make MCP server in PolicyLayer and add a rule for api: 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 Make. Nothing to install.
api 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 api 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 api. 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.
api is provided by the Make MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Make, 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.
202 Make tools catalogued and risk-classified — across an index of 43,000+ MCP servers.