sam_build

// WHEN AI AGENTS USE THIS TOOL

AI agents invoke sam_build to trigger processes or run actions in AWS Serverless MCP Server. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.

// WHY ENFORCE A POLICY ON SAM_BUILD

sam_build can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. Intercept enforces rate limits and validates arguments to keep execution within safe bounds.

// RECOMMENDED POLICY

Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.

aws-serverless-mcp-server.yaml

tools:
  sam_build:
    rules:
      - action: allow
        rate_limit:
          max: 10
          window: 60
        validate:
          required_args: true

See the full AWS Serverless MCP Server policy for all 32 tools.

// DETAILS

Tool Name sam_build

Category Execute

MCP Server AWS Serverless MCP Server MCP Server

Risk Level High

// MORE AWS SERVERLESS MCP SERVER TOOLS

Execute deploy_serverless_app_help Execute deploy_webapp Execute sam_deploy Execute sam_local_invoke Write configure_domain Write sam_init Write update_webapp_frontend Read describe_schema

View all 32 tools →

// WHAT CAN GO WRONG

Agents calling execute-class tools like sam_build have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

// OTHER EXECUTE TOOLS ACROSS MCP SERVERS

Other tools in the Execute risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.

Atv build_stake_tx Atv build_unstake_tx Acdp start_local Pentagonal pentagonal_audit Pentagonal pentagonal_compile ACR — Agent Composition Records orient_me

// IN CONTEXT OF HIGH RISK

sam_build is one of the high-risk operations in AWS Serverless MCP Server. For the full severity-focused view — only the high-risk tools with their recommended policies — see the breakdown for this server, or browse all high-risk tools across every MCP server.

// RELATED READING

// FAQ

What does the sam_build tool do? +

Builds a serverless application using AWS SAM (Serverless Application Model) CLI. Requirements: - AWS SAM CLI MUST be installed and configured in your environment - An application MUST already be initialized with 'sam_init' tool to create sam project structure. This command compiles your Lambda function and layer code, creates deployment artifacts, and prepares your application for deployment and local testing. It creates a .aws-sam directory that structures your application in a format and location that sam local and sam deploy require. For Zip functions, a .zip file archive is created, which contains your application code and its dependencies. For Image functions, a container image is created, which includes the base operating system, runtime, and extensions, in addition to your application code and its dependencies. By default, the functions and layers are built in parallel for faster builds. Usage tips: - Don't edit any code under the .aws-sam/build directory. Instead, update your original source code in your project folder and run sam build to update the .aws-sam/build directory. - When you modify your original files, run sam build to update the .aws-sam/build directory. - You may want the AWS SAM CLI to reference your project's original root directory instead of the .aws-sam directory, such as when developing and testing with sam local. Delete the .aws-sam directory or the AWS SAM template in the .aws-sam directory to have the AWS SAM CLI recognize your original project directory as the root project directory. When ready, run sam build again to create the .aws-sam directory. - When you run sam build, the .aws-sam/build directory gets overwritten each time. The .aws-sam directory does not. If you want to store files, such as logs, store them in .aws-sam to prevent them from being overwritten. Returns: Dict: SAM init command output. It is categorised as a Execute tool in the AWS Serverless MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on sam_build? +

Add a rule in your Intercept YAML policy under the tools section for sam_build. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the AWS Serverless MCP Server MCP server.

What risk level is sam_build? +

sam_build is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit sam_build? +

Yes. Add a rate_limit block to the sam_build rule in your Intercept 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.

How do I block sam_build completely? +

Set action: deny in the Intercept 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.

What MCP server provides sam_build? +

sam_build is provided by the AWS Serverless MCP Server MCP server (awslabs.aws-serverless-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Let agents act without letting them run wild.