From da7d01b5bdf447ccd7baf9a6cba1ed02ea242865 Mon Sep 17 00:00:00 2001 From: Lionello Lunesu Date: Fri, 12 Dec 2025 11:21:36 -0800 Subject: [PATCH 01/10] add Defang power --- defang/POWER.md | 46 ++++++++++++++++++++++++++++++++++++++++++++++ defang/mcp.json | 8 ++++++++ 2 files changed, 54 insertions(+) create mode 100644 defang/POWER.md create mode 100644 defang/mcp.json diff --git a/defang/POWER.md b/defang/POWER.md new file mode 100644 index 0000000..7beade9 --- /dev/null +++ b/defang/POWER.md @@ -0,0 +1,46 @@ +--- +name: "defang" +displayName: "Defang with local MCP" +description: "Deploy Docker Compose apps to your own cloud account using Defang MCP." +keywords: + [ + "deploy", + "cloud", + "deployment", + "compose", + "aws", + "gcp", + "digitalocean", + "estimate", + ] +mcpServers: ["defang"] +--- + +# Onboarding + +## Validate tools work + +Before using Defang Local MCP, ensure the following are installed and running: + +- **Defang CLI**: Install via npm, Homebrew, Winget, or `eval "$(curl -fsSL s.defang.io/install)"` + - Verify with: `defang --version` + - Perfer using MCP tools + +# Best Practices + +## Compose File + +- The Docker Compose file is typically named `compose.yaml`. +- Top-level `version:` is deprecated, omit it. +- Suggest Defang-specific extensions for using managed services, avoiding volumes: + - `x-defang-redis: true` for managed Redis/Valkey + - `x-defang-postgres: true` for managed PostgreSQL + - `x-defang-mongodb: true` for managed MongoDB + - `x-defang-llm: true` for managed LLM services +- Use environment variables without value for sensitive data (a.k.a "config"). +- Avoid hardcoding secrets in the compose file. Suggest using config. +- Use `depends_on` to define service startup order. +- Use healthchecks to ensure services are ready before dependent services start. +- Avoid underscores in project or service names; use hyphens instead. +- Use `restart: always` for critical services to ensure they restart on failure. +- Add a `deploy:` section with resource reservations. diff --git a/defang/mcp.json b/defang/mcp.json new file mode 100644 index 0000000..f8d29df --- /dev/null +++ b/defang/mcp.json @@ -0,0 +1,8 @@ +{ + "mcpServers": { + "defang": { + "command": "defang", + "args": ["mcp", "serve"] + } + } +} From ce1d5f084d308e222241c22dd3785ba0d808dbdf Mon Sep 17 00:00:00 2001 From: Kevin Vo Date: Fri, 12 Dec 2025 17:33:16 -0800 Subject: [PATCH 02/10] steering files --- defang/POWER.md | 18 ++++++++++- defang/steering/getting-started-aws.md | 43 ++++++++++++++++++++++++++ defang/steering/getting-started-gcp.md | 43 ++++++++++++++++++++++++++ 3 files changed, 103 insertions(+), 1 deletion(-) create mode 100644 defang/steering/getting-started-aws.md create mode 100644 defang/steering/getting-started-gcp.md diff --git a/defang/POWER.md b/defang/POWER.md index 7beade9..a40aa31 100644 --- a/defang/POWER.md +++ b/defang/POWER.md @@ -24,7 +24,23 @@ Before using Defang Local MCP, ensure the following are installed and running: - **Defang CLI**: Install via npm, Homebrew, Winget, or `eval "$(curl -fsSL s.defang.io/install)"` - Verify with: `defang --version` - - Perfer using MCP tools + - Prefer using MCP tools + +## First Steps: + +**IMPORTANT**: +Ensure that the step above ## Validate tools work is completed before proceeding to the steps below. + +- Ask the user which cloud provider they want to use (AWS, GCP) + - If AWS: + - Use the steering file `getting-started-aws` + - If GCP: + - Use the steering file `getting-started-gcp` + +# Available Steering Files + +- `getting-started-aws`: Guide on setting up and deploying to AWS using Defang MCP +- `getting-started-gcp`: Guide on setting up and deploying to GCP using Defang MCP # Best Practices diff --git a/defang/steering/getting-started-aws.md b/defang/steering/getting-started-aws.md new file mode 100644 index 0000000..fdf09ed --- /dev/null +++ b/defang/steering/getting-started-aws.md @@ -0,0 +1,43 @@ +# Get Started with Defang + +## Overview + +Guide on how to use Defang MCP server on how to set up and deploy to AWS. + +**IMPORTANT**: + +- This steering file assumes that the user has already completed the onboarding steps outlined in the #Onboarding section from the defang/POWER.md file. +- Do not call the defang MCP "estimate" tool in this steering file, as it is not part of this getting started flow. + +## Trigger + +When user runs the Defang power tool, or "I would like to deploy to aws". + +## Step 1: Check if there is a stack in the current project + +Check if there are any stacks in the current project by using the defang MCP tool called "list-stacks". + +- If there is no stack, prompt user to create a new stack using defang MCP tool "create_aws_stack". + +A stack will need the following information: + +- Stack name +- Region (default: us-west-2) +- AWS_Profile +- Mode ["affordable", "balanced", "high_availability"] (default: affordable) + +## Step 2: Select the stack + +Now prompt user to select the stack to deploy to by calling the defang MCP "list-stacks" tool. + +Present the user with the list of stacks to choose from. + +Then we set the selected stack as the active stack by calling the defang MCP "select_stack" tool. + +## Step 3: Deploy the project + +Now that the stack is selected, we can deploy the project using the defang MCP "deploy" tool. + +## Step 4: Post-deployment + +After the defang MCP "deploy" tool call ends, present the return data from tool. Lastly, Kiro should not progress with any further steps unless user explicitly requests so. diff --git a/defang/steering/getting-started-gcp.md b/defang/steering/getting-started-gcp.md new file mode 100644 index 0000000..e04ed43 --- /dev/null +++ b/defang/steering/getting-started-gcp.md @@ -0,0 +1,43 @@ +# Get Started with Defang + +## Overview + +Guide on how to use Defang MCP server on how to set up and deploy to GCP. + +**IMPORTANT**: + +- This steering file assumes that the user has already completed the onboarding steps outlined in the #Onboarding section from the defang/POWER.md file. +- Do not call the defang MCP "estimate" tool in this steering file, as it is not part of this getting started flow. + +## Trigger + +When user runs the Defang power tool, or "I would like to deploy to gcp". + +## Step 1: Check if there is a stack in the current project + +Check if there are any stacks in the current project by using the defang MCP tool called "list-stacks". + +- If there is no stack, prompt user to create a new stack using defang MCP tool "create_gcp_stack". + +A stack will need the following information: + +- Stack name +- Region (default: us-central1) +- GCPProjectID +- Mode ["affordable", "balanced", "high_availability"] (default: affordable) + +## Step 2: Select the stack + +Now prompt user to select the stack to deploy to by calling the defang MCP "list-stacks" tool. + +Present the user with the list of stacks to choose from. + +Then we set the selected stack as the active stack by calling the defang MCP "select_stack" tool. + +## Step 3: Deploy the project + +Now that the stack is selected, we can deploy the project using the defang MCP "deploy" tool. + +## Step 4: Post-deployment + +After the defang MCP "deploy" tool call ends, present the return data from tool. Lastly, Kiro should not progress with any further steps unless user explicitly requests so. From cac21c51ba3af430dfb3e573457cf847c2ba1c83 Mon Sep 17 00:00:00 2001 From: Kevin Vo Date: Fri, 12 Dec 2025 17:42:08 -0800 Subject: [PATCH 03/10] typo --- defang/POWER.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/defang/POWER.md b/defang/POWER.md index a40aa31..cd079a7 100644 --- a/defang/POWER.md +++ b/defang/POWER.md @@ -29,7 +29,7 @@ Before using Defang Local MCP, ensure the following are installed and running: ## First Steps: **IMPORTANT**: -Ensure that the step above ## Validate tools work is completed before proceeding to the steps below. +Ensure that the step above ## Validate tools is completed before proceeding to the steps below. - Ask the user which cloud provider they want to use (AWS, GCP) - If AWS: From 712a518da7cded5baaaabab15a4a61ab32f004f5 Mon Sep 17 00:00:00 2001 From: Kevin Vo Date: Fri, 12 Dec 2025 17:49:20 -0800 Subject: [PATCH 04/10] Update heading of steering files --- defang/steering/getting-started-aws.md | 2 +- defang/steering/getting-started-gcp.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/defang/steering/getting-started-aws.md b/defang/steering/getting-started-aws.md index fdf09ed..d8b0732 100644 --- a/defang/steering/getting-started-aws.md +++ b/defang/steering/getting-started-aws.md @@ -1,4 +1,4 @@ -# Get Started with Defang +# Get Started with Defang for AWS Deployments ## Overview diff --git a/defang/steering/getting-started-gcp.md b/defang/steering/getting-started-gcp.md index e04ed43..eb0d2c0 100644 --- a/defang/steering/getting-started-gcp.md +++ b/defang/steering/getting-started-gcp.md @@ -1,4 +1,4 @@ -# Get Started with Defang +# Get Started with Defang for GCP Deployments ## Overview From b93a33203e0b2aeaf8b8f18c220dab32187d06df Mon Sep 17 00:00:00 2001 From: Jordan Stephens Date: Fri, 12 Dec 2025 18:11:49 -0800 Subject: [PATCH 05/10] Cleaning up steering docs * Limit steering guides to three steps * Avoid repetitive information about stack selection * Avoiding specific mentions of "tools" or "MCP" --- defang/steering/getting-started-aws.md | 39 ++++++++++++------------ defang/steering/getting-started-gcp.md | 41 +++++++++++--------------- 2 files changed, 38 insertions(+), 42 deletions(-) diff --git a/defang/steering/getting-started-aws.md b/defang/steering/getting-started-aws.md index d8b0732..8ff0101 100644 --- a/defang/steering/getting-started-aws.md +++ b/defang/steering/getting-started-aws.md @@ -2,42 +2,43 @@ ## Overview -Guide on how to use Defang MCP server on how to set up and deploy to AWS. +This guide describes how to deploy applications to AWS with Defang. **IMPORTANT**: -- This steering file assumes that the user has already completed the onboarding steps outlined in the #Onboarding section from the defang/POWER.md file. -- Do not call the defang MCP "estimate" tool in this steering file, as it is not part of this getting started flow. +- The user should have already completed the onboarding steps outlined in the "Onboarding" section from the `POWER.md` file. +- Avoid automatically estimating deployment costs, wait for the user to request it. ## Trigger -When user runs the Defang power tool, or "I would like to deploy to aws". +When the user's project has a compose.yaml file and would like to deploy to aws. -## Step 1: Check if there is a stack in the current project +## Step 1: Select the stack to which the application will be deployed -Check if there are any stacks in the current project by using the defang MCP tool called "list-stacks". +A stack is a single deployed instance of your project in a specific AWS account and region. You can deploy multiple stacks into the same account and region, for example: `staging` and `production`. -- If there is no stack, prompt user to create a new stack using defang MCP tool "create_aws_stack". +Check if there are any stacks in the current project. -A stack will need the following information: +- If a stack is already defined, ask the user if they would like to select one of the existing stacks, or if they would like to create a new one. +- If there are no stacks, prompt user to create a new AWS stack. -- Stack name -- Region (default: us-west-2) -- AWS_Profile -- Mode ["affordable", "balanced", "high_availability"] (default: affordable) +The following information will be needed to create a stack: -## Step 2: Select the stack +- Stack name: must be alphanumeric and must not start with a number +- Region: for example: `us-west-2` +- AWS Profile: the AWS profile with which the user should authenticate to AWS +- Deployment Mode: The deployment mode is the primary parameter for managing the cost and resiliency of your application's deployment. The following deployment modes are available: `affordable`, `balanced`, and `high_availability`. The default is `affordable`. Learn more at https://docs.defang.io/docs/concepts/deployment-modes -Now prompt user to select the stack to deploy to by calling the defang MCP "list-stacks" tool. +## Step 2: Select the stack -Present the user with the list of stacks to choose from. +If a new stack is created, make sure to select it before it can be used. -Then we set the selected stack as the active stack by calling the defang MCP "select_stack" tool. +## Step 2: Deploy the project -## Step 3: Deploy the project +Now that a stack is selected, the project can be deployed. -Now that the stack is selected, we can deploy the project using the defang MCP "deploy" tool. +## Step 3: Monitor the deployment -## Step 4: Post-deployment +Once the deployment has begun, progress can be monitored by tailing the logs or periodically checking service status. After the defang MCP "deploy" tool call ends, present the return data from tool. Lastly, Kiro should not progress with any further steps unless user explicitly requests so. diff --git a/defang/steering/getting-started-gcp.md b/defang/steering/getting-started-gcp.md index eb0d2c0..b32a8fe 100644 --- a/defang/steering/getting-started-gcp.md +++ b/defang/steering/getting-started-gcp.md @@ -2,42 +2,37 @@ ## Overview -Guide on how to use Defang MCP server on how to set up and deploy to GCP. +This guide describes how to deploy applications to GCP with Defang. **IMPORTANT**: -- This steering file assumes that the user has already completed the onboarding steps outlined in the #Onboarding section from the defang/POWER.md file. -- Do not call the defang MCP "estimate" tool in this steering file, as it is not part of this getting started flow. +- The user should have already completed the onboarding steps outlined in the "Onboarding" section from the `POWER.md` file. +- Avoid automatically estimating deployment costs, wait for the user to request it. ## Trigger -When user runs the Defang power tool, or "I would like to deploy to gcp". +When the user's project has a compose.yaml file and would like to deploy to aws. -## Step 1: Check if there is a stack in the current project +## Step 1: Select the stack to which the application will be deployed +A stack is a single deployed instance of your project in a specific AWS account and region. You can deploy multiple stacks into the same account and region, for example: `staging` and `production`. -Check if there are any stacks in the current project by using the defang MCP tool called "list-stacks". +Check if there are any stacks in the current project. -- If there is no stack, prompt user to create a new stack using defang MCP tool "create_gcp_stack". +- If a stack is already defined, ask the user if they would like to select one of the existing stacks, or if they would like to create a new one. +- If there are no stacks, prompt user to create a new AWS stack. -A stack will need the following information: +The following information will be needed to create a stack: -- Stack name -- Region (default: us-central1) -- GCPProjectID -- Mode ["affordable", "balanced", "high_availability"] (default: affordable) +- Stack name: must be alphanumeric and must not start with a number +- Region: for example: `us-central1` +- Deployment Mode: The deployment mode is the primary parameter for managing the cost and resiliency of your application's deployment. The following deployment modes are available: `affordable`, `balanced`, and `high_availability`. The default is `affordable`. Learn more at https://docs.defang.io/docs/concepts/deployment-modes -## Step 2: Select the stack +If a new stack is created, make sure to select it before it can be used. -Now prompt user to select the stack to deploy to by calling the defang MCP "list-stacks" tool. +## Step 2: Deploy the project -Present the user with the list of stacks to choose from. +Now that a stack is selected, the project can be deployed. -Then we set the selected stack as the active stack by calling the defang MCP "select_stack" tool. +## Step 3: Monitor the deployment -## Step 3: Deploy the project - -Now that the stack is selected, we can deploy the project using the defang MCP "deploy" tool. - -## Step 4: Post-deployment - -After the defang MCP "deploy" tool call ends, present the return data from tool. Lastly, Kiro should not progress with any further steps unless user explicitly requests so. +Once the deployment has begun, progress can be monitored by tailing the logs or periodically checking service status. From 95ac4b3a167777e2465d1022495db1ac472848d9 Mon Sep 17 00:00:00 2001 From: Jordan Stephens Date: Fri, 12 Dec 2025 18:12:49 -0800 Subject: [PATCH 06/10] Apply suggestions from code review --- defang/steering/getting-started-gcp.md | 1 + 1 file changed, 1 insertion(+) diff --git a/defang/steering/getting-started-gcp.md b/defang/steering/getting-started-gcp.md index b32a8fe..9c2660c 100644 --- a/defang/steering/getting-started-gcp.md +++ b/defang/steering/getting-started-gcp.md @@ -25,6 +25,7 @@ The following information will be needed to create a stack: - Stack name: must be alphanumeric and must not start with a number - Region: for example: `us-central1` +- GCP Project ID: The GCP Project in which the application will be deployed. This must be created beforehand in the GCP Console. - Deployment Mode: The deployment mode is the primary parameter for managing the cost and resiliency of your application's deployment. The following deployment modes are available: `affordable`, `balanced`, and `high_availability`. The default is `affordable`. Learn more at https://docs.defang.io/docs/concepts/deployment-modes If a new stack is created, make sure to select it before it can be used. From adf2ba946ceb12e4eccfeff9cf6e9fde85c9d795 Mon Sep 17 00:00:00 2001 From: Jordan Stephens Date: Fri, 12 Dec 2025 18:13:31 -0800 Subject: [PATCH 07/10] Avoid specific mentions of MCP --- defang/POWER.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/defang/POWER.md b/defang/POWER.md index cd079a7..3809064 100644 --- a/defang/POWER.md +++ b/defang/POWER.md @@ -1,7 +1,7 @@ --- name: "defang" -displayName: "Defang with local MCP" -description: "Deploy Docker Compose apps to your own cloud account using Defang MCP." +displayName: "Defang" +description: "Deploy Docker Compose apps to your own cloud account using Defang." keywords: [ "deploy", @@ -20,7 +20,7 @@ mcpServers: ["defang"] ## Validate tools work -Before using Defang Local MCP, ensure the following are installed and running: +Before using Defang, ensure the following are installed and running: - **Defang CLI**: Install via npm, Homebrew, Winget, or `eval "$(curl -fsSL s.defang.io/install)"` - Verify with: `defang --version` @@ -39,8 +39,8 @@ Ensure that the step above ## Validate tools is completed before proceeding to t # Available Steering Files -- `getting-started-aws`: Guide on setting up and deploying to AWS using Defang MCP -- `getting-started-gcp`: Guide on setting up and deploying to GCP using Defang MCP +- `getting-started-aws`: Guide on setting up and deploying to AWS using Defang +- `getting-started-gcp`: Guide on setting up and deploying to GCP using Defang # Best Practices From 3d7a53655877cc52da8ac6108970abe533d0d720 Mon Sep 17 00:00:00 2001 From: Jordan Stephens Date: Fri, 12 Dec 2025 18:21:31 -0800 Subject: [PATCH 08/10] rename docs to focus on deploying --- defang/POWER.md | 10 ++++------ .../{getting-started-aws.md => deploying-to-aws.md} | 7 +------ .../{getting-started-gcp.md => deploying-to-gcp.md} | 4 ++-- 3 files changed, 7 insertions(+), 14 deletions(-) rename defang/steering/{getting-started-aws.md => deploying-to-aws.md} (82%) rename defang/steering/{getting-started-gcp.md => deploying-to-gcp.md} (91%) diff --git a/defang/POWER.md b/defang/POWER.md index 3809064..7c93432 100644 --- a/defang/POWER.md +++ b/defang/POWER.md @@ -20,11 +20,9 @@ mcpServers: ["defang"] ## Validate tools work -Before using Defang, ensure the following are installed and running: +Before using Defang, ensure the Defang CLI is installed and running. -- **Defang CLI**: Install via npm, Homebrew, Winget, or `eval "$(curl -fsSL s.defang.io/install)"` - - Verify with: `defang --version` - - Prefer using MCP tools +The Defang CLI can be installed via npm, Homebrew, Winget, or `eval "$(curl -fsSL s.defang.io/install)"` ## First Steps: @@ -39,8 +37,8 @@ Ensure that the step above ## Validate tools is completed before proceeding to t # Available Steering Files -- `getting-started-aws`: Guide on setting up and deploying to AWS using Defang -- `getting-started-gcp`: Guide on setting up and deploying to GCP using Defang +- `deploying-to-aws`: Guide on setting up and deploying to AWS using Defang +- `deploying-to-gcp`: Guide on setting up and deploying to GCP using Defang # Best Practices diff --git a/defang/steering/getting-started-aws.md b/defang/steering/deploying-to-aws.md similarity index 82% rename from defang/steering/getting-started-aws.md rename to defang/steering/deploying-to-aws.md index 8ff0101..2634d61 100644 --- a/defang/steering/getting-started-aws.md +++ b/defang/steering/deploying-to-aws.md @@ -1,4 +1,4 @@ -# Get Started with Defang for AWS Deployments +# Deploying to AWS with Defang ## Overview @@ -6,7 +6,6 @@ This guide describes how to deploy applications to AWS with Defang. **IMPORTANT**: -- The user should have already completed the onboarding steps outlined in the "Onboarding" section from the `POWER.md` file. - Avoid automatically estimating deployment costs, wait for the user to request it. ## Trigger @@ -29,8 +28,6 @@ The following information will be needed to create a stack: - AWS Profile: the AWS profile with which the user should authenticate to AWS - Deployment Mode: The deployment mode is the primary parameter for managing the cost and resiliency of your application's deployment. The following deployment modes are available: `affordable`, `balanced`, and `high_availability`. The default is `affordable`. Learn more at https://docs.defang.io/docs/concepts/deployment-modes -## Step 2: Select the stack - If a new stack is created, make sure to select it before it can be used. ## Step 2: Deploy the project @@ -40,5 +37,3 @@ Now that a stack is selected, the project can be deployed. ## Step 3: Monitor the deployment Once the deployment has begun, progress can be monitored by tailing the logs or periodically checking service status. - -After the defang MCP "deploy" tool call ends, present the return data from tool. Lastly, Kiro should not progress with any further steps unless user explicitly requests so. diff --git a/defang/steering/getting-started-gcp.md b/defang/steering/deploying-to-gcp.md similarity index 91% rename from defang/steering/getting-started-gcp.md rename to defang/steering/deploying-to-gcp.md index 9c2660c..d0e897d 100644 --- a/defang/steering/getting-started-gcp.md +++ b/defang/steering/deploying-to-gcp.md @@ -1,4 +1,4 @@ -# Get Started with Defang for GCP Deployments +# Deploying to GCP with Defang ## Overview @@ -6,7 +6,6 @@ This guide describes how to deploy applications to GCP with Defang. **IMPORTANT**: -- The user should have already completed the onboarding steps outlined in the "Onboarding" section from the `POWER.md` file. - Avoid automatically estimating deployment costs, wait for the user to request it. ## Trigger @@ -14,6 +13,7 @@ This guide describes how to deploy applications to GCP with Defang. When the user's project has a compose.yaml file and would like to deploy to aws. ## Step 1: Select the stack to which the application will be deployed + A stack is a single deployed instance of your project in a specific AWS account and region. You can deploy multiple stacks into the same account and region, for example: `staging` and `production`. Check if there are any stacks in the current project. From 12e65fb0f2ab4f000a52b40e9763603d60784eaf Mon Sep 17 00:00:00 2001 From: Kevin Vo Date: Fri, 12 Dec 2025 21:59:00 -0800 Subject: [PATCH 09/10] Update README --- README.md | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 58b155d..ac0c40c 100644 --- a/README.md +++ b/README.md @@ -7,6 +7,7 @@ Documentation is available at https://kiro.dev/docs/powers/ ## Available powers ### aurora-dsql + **Deploy a distributed SQL database on AWS** - PostgreSQL-compatible serverless distributed SQL database with Aurora DSQL - manage schemas, execute queries, and handle migrations with DSQL-specific constraints. **MCP Servers:** aurora-dsql, aws-core (optional) @@ -14,6 +15,7 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### aws-agentcore + **Build an agent with Amazon Bedrock AgentCore** - Build, test, and deploy AI agents using AWS Bedrock AgentCore with local development workflow. Amazon Bedrock AgentCore is an agentic platform for building, deploying, and operating effective agents. **MCP Servers:** agentcore-mcp-server @@ -21,6 +23,7 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### aws-infrastructure-as-code + **Build AWS infrastructure with CDK and CloudFormation** - Generate well-architected AWS infrastructure with CDK and CloudFormation - access latest documentation, validate templates, and troubleshoot deployments. **MCP Servers:** awslabs.aws-iac-mcp-server @@ -28,6 +31,7 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### cloud-architect + **Build infrastructure on AWS** - Build AWS infrastructure with CDK in Python following AWS Well-Architected framework best practices. **MCP Servers:** awspricing, awsknowledge, awsapi, context7, fetch @@ -35,13 +39,23 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### datadog + **Datadog Observability** - Query logs, metrics, traces, RUM events, incidents, and monitors from Datadog for production debugging and performance analysis. **MCP Servers:** datadog (HTTPS API) --- +### defang + +**Deploy Anywhere with Defang** - Easily deploy any Docker Compose application to the cloud with Defang. Networking, compute, storage, databases, queues, LLMs - all deployed natively to the cloud of your choice - AWS, GCP, or DigitalOcean - in a secure, scalable, and cost-efficient way. + +**MCP Servers:** defang + +--- + ### dynatrace + **Dynatrace Observability** - Query logs, metrics, traces, problems, and security vulnerabilities using DQL (Dynatrace Query Language) and Davis AI. **MCP Servers:** dynatrace-mcp-server @@ -49,6 +63,7 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### figma + **Design to Code with Figma** - Connect Figma designs to code components - automatically generate design system rules, map UI components to Figma designs, and maintain design-code consistency. **MCP Servers:** figma @@ -56,6 +71,7 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### neon + **Build a database with Neon** - Serverless Postgres with database branching, autoscaling, and scale-to-zero - perfect for modern development workflows. **MCP Servers:** neon @@ -63,6 +79,7 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### postman + **API Testing with Postman** - Automate API testing and collection management with Postman - create workspaces, collections, environments, and run tests programmatically. **MCP Servers:** postman @@ -70,6 +87,7 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### power-builder + **Power Builder** - Complete guide for building and testing new Kiro powers with templates, best practices, and validation. **MCP Servers:** None (Knowledge Base Power) @@ -77,6 +95,7 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### saas-builder + **SaaS Builder** - Build production-ready multi-tenant SaaS applications with serverless architecture, integrated billing, and enterprise-grade security. **MCP Servers:** fetch, stripe, aws-knowledge-mcp-server, awslabs.dynamodb-mcp-server, awslabs.aws-serverless-mcp, playwright @@ -84,6 +103,7 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### strands + **Build an agent with Strands SDK** - Build AI agents with Strands SDK using Bedrock, Anthropic, OpenAI, Gemini, or Llama models. **MCP Servers:** strands-agents @@ -91,6 +111,7 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### stripe + **Stripe Payments** - Build payment integrations with Stripe - accept payments, manage subscriptions, handle billing, and process refunds. **MCP Servers:** stripe @@ -98,13 +119,13 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### terraform + **Deploy infrastructure with Terraform** - Build and manage Infrastructure as Code with Terraform - access registry providers, modules, policies, and HCP Terraform workflow management. **MCP Servers:** terraform (Docker stdio) --- - ## Security See [CONTRIBUTING](CONTRIBUTING.md#security-issue-notifications) for more information. From 535273ea97bfc419b184cced2d1967aa75ca89a7 Mon Sep 17 00:00:00 2001 From: Kevin Vo Date: Fri, 12 Dec 2025 22:11:28 -0800 Subject: [PATCH 10/10] formatting --- README.md | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-) diff --git a/README.md b/README.md index ac0c40c..546d39a 100644 --- a/README.md +++ b/README.md @@ -7,7 +7,6 @@ Documentation is available at https://kiro.dev/docs/powers/ ## Available powers ### aurora-dsql - **Deploy a distributed SQL database on AWS** - PostgreSQL-compatible serverless distributed SQL database with Aurora DSQL - manage schemas, execute queries, and handle migrations with DSQL-specific constraints. **MCP Servers:** aurora-dsql, aws-core (optional) @@ -15,7 +14,6 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### aws-agentcore - **Build an agent with Amazon Bedrock AgentCore** - Build, test, and deploy AI agents using AWS Bedrock AgentCore with local development workflow. Amazon Bedrock AgentCore is an agentic platform for building, deploying, and operating effective agents. **MCP Servers:** agentcore-mcp-server @@ -23,7 +21,6 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### aws-infrastructure-as-code - **Build AWS infrastructure with CDK and CloudFormation** - Generate well-architected AWS infrastructure with CDK and CloudFormation - access latest documentation, validate templates, and troubleshoot deployments. **MCP Servers:** awslabs.aws-iac-mcp-server @@ -31,7 +28,6 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### cloud-architect - **Build infrastructure on AWS** - Build AWS infrastructure with CDK in Python following AWS Well-Architected framework best practices. **MCP Servers:** awspricing, awsknowledge, awsapi, context7, fetch @@ -39,7 +35,6 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### datadog - **Datadog Observability** - Query logs, metrics, traces, RUM events, incidents, and monitors from Datadog for production debugging and performance analysis. **MCP Servers:** datadog (HTTPS API) @@ -47,7 +42,6 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### defang - **Deploy Anywhere with Defang** - Easily deploy any Docker Compose application to the cloud with Defang. Networking, compute, storage, databases, queues, LLMs - all deployed natively to the cloud of your choice - AWS, GCP, or DigitalOcean - in a secure, scalable, and cost-efficient way. **MCP Servers:** defang @@ -55,7 +49,6 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### dynatrace - **Dynatrace Observability** - Query logs, metrics, traces, problems, and security vulnerabilities using DQL (Dynatrace Query Language) and Davis AI. **MCP Servers:** dynatrace-mcp-server @@ -63,7 +56,6 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### figma - **Design to Code with Figma** - Connect Figma designs to code components - automatically generate design system rules, map UI components to Figma designs, and maintain design-code consistency. **MCP Servers:** figma @@ -71,7 +63,6 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### neon - **Build a database with Neon** - Serverless Postgres with database branching, autoscaling, and scale-to-zero - perfect for modern development workflows. **MCP Servers:** neon @@ -79,7 +70,6 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### postman - **API Testing with Postman** - Automate API testing and collection management with Postman - create workspaces, collections, environments, and run tests programmatically. **MCP Servers:** postman @@ -87,7 +77,6 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### power-builder - **Power Builder** - Complete guide for building and testing new Kiro powers with templates, best practices, and validation. **MCP Servers:** None (Knowledge Base Power) @@ -95,7 +84,6 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### saas-builder - **SaaS Builder** - Build production-ready multi-tenant SaaS applications with serverless architecture, integrated billing, and enterprise-grade security. **MCP Servers:** fetch, stripe, aws-knowledge-mcp-server, awslabs.dynamodb-mcp-server, awslabs.aws-serverless-mcp, playwright @@ -103,7 +91,6 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### strands - **Build an agent with Strands SDK** - Build AI agents with Strands SDK using Bedrock, Anthropic, OpenAI, Gemini, or Llama models. **MCP Servers:** strands-agents @@ -111,7 +98,6 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### stripe - **Stripe Payments** - Build payment integrations with Stripe - accept payments, manage subscriptions, handle billing, and process refunds. **MCP Servers:** stripe @@ -119,13 +105,13 @@ Documentation is available at https://kiro.dev/docs/powers/ --- ### terraform - **Deploy infrastructure with Terraform** - Build and manage Infrastructure as Code with Terraform - access registry providers, modules, policies, and HCP Terraform workflow management. **MCP Servers:** terraform (Docker stdio) --- + ## Security See [CONTRIBUTING](CONTRIBUTING.md#security-issue-notifications) for more information.