Clarify available prebuilt MCP server images in overview and add links to them

custom_dc/quickstart.md

@@ -15,6 +15,7 @@ This is step 1 of the [recommended workflow](/custom_dc/index.html#workflow).
 * TOC
 {:toc}
 
+{: #overview}
 ## System overview
 
 The instructions in this page use the following setup:

mcp/host_server.md

@@ -37,7 +37,7 @@ To instruct Gemini CLI to start up a local server using Stdio, replace the `data
 
 <pre>
 {
-   // ...
+   ...
    "mcpServers": {
       "datacommons-mcp": {
          "command": "uvx",
@@ -50,7 +50,7 @@ To instruct Gemini CLI to start up a local server using Stdio, replace the `data
          "env": "<var>YOUR DC API KEY</var>"
       }
    }
-   // ...
+   ...
 }
 </pre>
 
@@ -127,13 +127,12 @@ The server is addressable with the endpoint `mcp`. For example, `http://my-mcp-s
 #### Sample agent
 
 1. Modify [`basic_agent/agent.py`](https://github.com/datacommonsorg/agent-toolkit/blob/main/packages/datacommons-mcp/examples/sample_agents/basic_agent/agent.py){: target="_blank"} as follows:
-
    <pre>
    from google.adk.tools.mcp_tool.mcp_toolset import (
    MCPToolset,
    StreamableHTTPConnectionParams
    )
-   ...
+   #...
    root_agent = LlmAgent(
       # ...
       tools=[McpToolset(
@@ -146,7 +145,7 @@ The server is addressable with the endpoint `mcp`. For example, `http://my-mcp-s
       )
     ],
    )  
-</pre>
+   </pre>
 1. Customize the agent as desired, as described in [Customize the agent](run_tools.md#customize-agent).
 1. [Run the startup commands](run_tools.md#run-sample) as usual.
 

mcp/index.md

@@ -22,8 +22,9 @@ For base Data Commons, the server is available as a hosted managed deployment to
 ![base Data Commons](/assets/images/mcp1.png)
 
 You can also run your own MCP server locally, or in Google Cloud Platform. If you want to use the server to query a Custom Data Commons instance, you _must_ run your own. The server is available as:
--  A prebuilt Python package for running locally
--  A prebuilt Docker image for running in a Google Cloud Run service
+-  A prebuilt [Python package](https://pypi.org/project/datacommons-mcp/){: target="_blank"} for running locally 
+-  A prebuilt standalone [Docker image](https://console.cloud.google.com/artifacts/docker/datcom-ci/us/gcr.io/datacommons-mcp-server?project=datcom-ci){: target="_blank"} for running in a cloud service
+-  Bundled with the [Custom Data Commons Docker services image](/custom_dc/quickstart.html#overview) for running in Google Cloud Run (for Custom Data Commons only)
 
 ![base or Custom Data Commons](/assets/images/mcp2.png)
 

mcp/run_tools.md

@@ -154,7 +154,7 @@ In addition to the Data Commons API key, you must install the following:
 To configure Gemini CLI to connect to the Data Commons server, edit the relevant `settings.json` file (e.g. `~/.gemini/settings.json`) to add the following:
 <pre>
 {
-   // ...
+   ...
    "mcpServers": {
      "datacommons-mcp": {
          "httpUrl": "https://api.datacommons.org/mcp",
@@ -166,7 +166,7 @@ To configure Gemini CLI to connect to the Data Commons server, edit the relevant
          }
       }
    }
-   // ...
+   ...
 }
 </pre>