Fix package READMEs: correct install name, binary refs, and wording (#39)

- sdk: Fix pip install name (agent-builder-sdk → agent-builder-sdk-aws-transform)
- sdk: Fix binary_location to reference agentic-mcp, not dev mcp-server
- agentic-mcp-server: Remove "platform" wording
- mcp-server: Make client-agnostic (works with any MCP client, not just Kiro)

Author: lzongren

packages/agentic-mcp-server/README.md

@@ -1,6 +1,6 @@
 # Agent Builder Agentic MCP Server
 
-An [MCP](https://modelcontextprotocol.io/) server that agents built with the [Agent Builder SDK](https://pypi.org/project/agent-builder-sdk-aws-transform/) use at runtime to talk to the [AWS Transform](https://aws.amazon.com/transform/) platform.
+An [MCP](https://modelcontextprotocol.io/) server that agents built with the [Agent Builder SDK](https://pypi.org/project/agent-builder-sdk-aws-transform/) use at runtime to communicate with [AWS Transform](https://aws.amazon.com/transform/).
 
 ## Installation
 

packages/mcp-server/README.md

@@ -1,11 +1,8 @@
 # Agent Builder MCP Server
-# Agent Builder MCP Server
-
-An [MCP](https://modelcontextprotocol.io/) server that gives [Kiro](https://kiro.dev/) the tools and knowledge it needs to build, deploy, and manage agents on [AWS Transform](https://aws.amazon.com/transform/).
 
-With this server configured, Kiro gains first-class help for AWS Transform agent development: searching documentation, scaffolding agent code, deploying to AWS, and managing runtime operations.
+An [MCP](https://modelcontextprotocol.io/) server that provides tools and knowledge for building, deploying, and managing agents on [AWS Transform](https://aws.amazon.com/transform/).
 
-Pair it with the [**AWS Transform Agent Builder Kiro Power**](https://kiro.dev/powers/) to unlock the full end-to-end experience — the Power provides curated steering rules and workflows that guide Kiro through the entire agent-building process on top of this server's tools.
+This server works with any MCP-compatible client — [Kiro](https://kiro.dev/), Claude Code, Cursor, Windsurf, or any other IDE/tool that supports the Model Context Protocol.
 
 ## Installation
 
@@ -17,7 +14,13 @@ This installs an `agent-builder-mcp` command that speaks MCP over stdio.
 
 ## Quick start
 
-Add the server to Kiro's MCP configuration:
+### With Kiro (recommended)
+
+Install the [**AWS Transform Agent Toolkit**](https://kiro.dev/powers/#aws-transform-agent-toolkit) Kiro Power for the full guided experience — it configures this MCP server automatically and adds steering rules that guide Kiro through the entire agent-building process.
+
+### With any MCP client
+
+Add the server to your MCP configuration:
 
 ```json
 {
@@ -30,7 +33,7 @@ Add the server to Kiro's MCP configuration:
 }
 ```
 
-Restart Kiro. It will now have access to the agent-builder tool set.
+Restart your IDE/tool. It will now have access to the agent-builder tool set.
 
 ## What it provides
 
@@ -43,8 +46,6 @@ Tools are grouped into six categories:
 - **Validation** — check agent manifests and configurations before deployment.
 - **CloudWatch** — query agent logs and metrics.
 
-Ask Kiro "what agent-builder tools do you have?" and it will list the exact set available in your installed version.
-
 ## Requirements
 
 - Python 3.11+

packages/sdk/README.md

@@ -12,7 +12,7 @@ The SDK wraps the common concerns — HTTP server, request routing, agent lifecy
 ## Installation
 
 ```bash
-pip install agent-builder-sdk
+pip install agent-builder-sdk-aws-transform
 ```
 
 ## Building an orchestrator
@@ -72,7 +72,7 @@ def main():
         agent_factory=agent_factory,
         host="0.0.0.0",
         port=8080,
-        binary_location="./agent-builder-mcp",
+        binary_location="agent-builder-agentic-mcp",
         storage_dir="/tmp/my_agent",
         checkpoint_strategy="conversation",  # optional, enables checkpointing
         checkpoint_interval=10,              # optional, enables checkpointing
@@ -132,7 +132,7 @@ def main():
         agent_factory=agent_factory,
         host="0.0.0.0",
         port=8080,
-        binary_location="./agent-builder-mcp",
+        binary_location="agent-builder-agentic-mcp",
     )
     server.start()
 
@@ -145,7 +145,7 @@ if __name__ == "__main__":
 
 - Python 3.11+
 - AWS credentials configured (standard `boto3` credential chain), with Bedrock access for model inference
-- The `agent-builder-mcp` binary on disk — see [agent-builder-mcp-aws-transform](https://pypi.org/project/agent-builder-mcp-aws-transform/)
+- The `agent-builder-agentic-mcp` binary on disk — see [agent-builder-agentic-mcp-aws-transform](https://pypi.org/project/agent-builder-agentic-mcp-aws-transform/)
 
 ## License