Docker MCP Error:"'NoneType' object has no attribute 'error'"

Docker Hub MCP Catalog
,
1

I’m using the Docker MCP facility and it works for Playwright but I’m having issues with the AWS MCP servers. I’ve added ‘core’ and the DynamoDB server, but when I try and ask something like “What dynamodb tabes can you see?” I get this error:

MCP_DOCKER - execute_dynamodb_command (MCP)(command: "aws dynamodb list-tables")
  ⎿  "'NoneType' object has no attribute 'error'"

I can invoke the tool directly from the command line and get the same error:

docker mcp tools call execute_dynamodb_command command=‘aws dynamodb list-tables’
Tool call took: 1.387119833s
“‘NoneType’ object has no attribute ‘error’”

The tool is available:

docker mcp tools ls
34 tools:
 - browser_click - Click
 - browser_close - Close browser
 - browser_console_messages - Get console messages
 - browser_drag - Drag mouse
 - browser_evaluate - Evaluate JavaScript
 - browser_file_upload - Upload files
 - browser_fill_form - Fill form
 - browser_handle_dialog - Handle a dialog
 - browser_hover - Hover mouse
 - browser_install - Install the browser specified in the config
 - browser_navigate - Navigate to a URL
 - browser_navigate_back - Go back
 - browser_network_requests - List network requests
 - browser_press_key - Press a key
 - browser_resize - Resize browser window
 - browser_run_code - Run Playwright code
 - browser_select_option - Select option
 - browser_snapshot - Page snapshot
 - browser_tabs - Manage tabs
 - browser_take_screenshot - Take a screenshot
 - browser_type - Type text
 - browser_wait_for - Wait for
 - code-mode - Create a JavaScript-enabled tool that combines multiple MCP server tools.
 - dynamodb_data_model_validation - Validates and tests DynamoDB data models against DynamoDB Local.
 - dynamodb_data_modeling - Retrieves the complete DynamoDB Data Modeling Expert prompt.
 - execute_dynamodb_command - Execute AWSCLI DynamoDB commands.
 - mcp-add - Add a new MCP server to the session.
 - mcp-config-set - Set configuration for an MCP server.
 - mcp-create-profile - Create or update a profile with the current gateway state.
 - mcp-exec - Execute a tool that exists in the current session.
 - mcp-find - Find MCP servers in the current catalog by name, title, or description.
 - mcp-remove - Remove an MCP server from the registry and reload the configuration.
 - prompt_understanding - MCP-CORE Prompt Understanding.
 - source_db_analyzer - Analyzes your source database to extract schema and access patterns for DynamoDB Data Modeling.

Anyone had any success here?

2

Did you configure the credentials (doc) correctly?

3

I did. yes. I’m not entirely sure how the dockerized MCP server gets access to my aws config however. Is my .aws folder mounted behind the scenes? The cloudwatch server has the same configuration requirements: region and profile. Using that MCP server with the same config I get:

docker mcp tools call describe_log_groups
Tool call took: 1.96659s
error calling tool describe_log_groups: Error executing tool describe_log_groups: The config profile (xxxxxx) could not be found
4

THat would explain why it asks for the profile. You can start the mcp server and inspect the container, to see if it has additional mounts. After all those are just containers.

5

Judging by the aws mcp docs, the auth information must be either mapped as volume, or provided as enviornment variable: https://github.com/awslabs/mcp?tab=readme-ov-file#running-mcp-servers-in-containers

6

Yes, that was my reading too. I thought perhaps the MCP toolkit might abstract away all the config to a one-click solution but Perhaps I do need to spin up the server containers myself. Thanks.