AI agents invoke sam_build to trigger actions in Amazon Location Service 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.
SAM build executes a build process on application code, which involves running compilation steps, dependency resolution, and code transformation—hallmarks of the Execute category.
From the tool's definition Tool name 'sam_build' indicates AWS SAM (Serverless Application Model) build execution. The sibling tools on this server include 'analyze_cdk_project' and other infrastructure/deployment-related operations, suggesting this server manages AWS infrastructure…
Documented attack patterns abuse exactly the kind of access sam_build gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Amazon Location Service MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for sam_build:
{
"version": "1",
"default": "deny",
"tools": {
"sam_build": {
"limits": [
{
"counter": "sam_build_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} sam_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.
sam_build. It is categorised as a Execute tool in the Amazon Location Service MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Amazon Location Service MCP Server MCP server in PolicyLayer and add a rule for sam_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 Amazon Location Service MCP Server. Nothing to install.
sam_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 sam_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 sam_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.
sam_build is provided by the Amazon Location Service MCP Server MCP server (awslabs.aws-location-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Amazon Location Service 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.
805 Amazon Location Service MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.