AI agents invoke deploy_project to trigger actions in Neptune 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.
This tool executes deployment operations to AWS infrastructure, which is a significant external operation whose effects depend on what project is being deployed and the infrastructure inferred.
From the tool's definition Tool named 'deploy_project' with no description; part of a server that 'deploy applications to AWS with DevOps capabilities' and 'automatically inferring infrastructure needs from code.' Deploying to AWS is an Execute action (triggers external operations with…
Documented attack patterns abuse exactly the kind of access deploy_project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Neptune MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for deploy_project:
{
"version": "1",
"default": "deny",
"tools": {
"deploy_project": {
"limits": [
{
"counter": "deploy_project_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}deploy_project 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.
deploy_project. It is categorised as a Execute tool in the Neptune MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Neptune MCP Server MCP server in PolicyLayer and add a rule for deploy_project: 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 Neptune MCP Server. Nothing to install.
deploy_project 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 deploy_project 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 deploy_project. 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.
deploy_project is provided by the Neptune MCP Server MCP server (shuttle-hq/neptune-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Neptune MCP 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.
15 Neptune MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.