Ext Ops Panel
Open dashboard
Comparison

AWS Bedrock AgentCore vs io.github.microsoft/playwright-mcp

AWS Bedrock AgentCore is an MCP server published by awslabs. Marketplaces we read that list it: 1 (Docker MCP Catalog). io.github.microsoft/playwright-mcp is an MCP server published by microsoft. Marketplaces we read that list it: 4 (Official MCP Registry, Claude Code: claude-plugins-official, Cursor: cursor/plugins, Docker MCP Catalog). As of our marketplace pass on 2026-10-14. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.

Where each is published

Where each is published
MarketplaceAWS Bedrock AgentCoreio.github.microsoft/playwright-mcp
Docker MCP Catalog Listed
Version: sha256:df610a7a056f
Forks (GitHub): 1 805
Pulls (Docker Hub): 20 000
Stars (Docker Hub): 0
Stars (GitHub): 9 776
Not marked · First seen
Listed
Version: sha256:8771dc4666e7
Forks (GitHub): 3 244
Pulls (Docker Hub): 2 428 126
Stars (Docker Hub): 38
Stars (GitHub): 38 101
Not marked · First seen
Official MCP Registry Not listed Listed
Version: 0.0.82
Downloads/month (npm): 30 500 978
Downloads/week (npm): 6 524 222
Forks (GitHub): 3 244
Stars (GitHub): 38 101
Not marked · First seen
Claude Code: claude-plugins-official Not listed Listed
Version: not stated
Forks (GitHub): 4 268
Stars (GitHub): 37 981
Not marked · First seen
Cursor: cursor/plugins Not listed Listed
Version: 1.0.0
Forks (GitHub): 1 086
Stars (GitHub): 11 186
Not marked · First seen

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

The facts side by side

AWS Bedrock AgentCore vs io.github.microsoft/playwright-mcp
FactAWS Bedrock AgentCoreio.github.microsoft/playwright-mcp
Marketplaces that list it (differs)1 (worse)4 (better)
Stars (GitHub) (differs)9 776 (worse)38 101 (better)
Pulls (Docker Hub) (differs)20 000 (worse)2 428 126 (better)
Forks (GitHub) (differs)1 805 (worse)4 268 (better)
Last releaseNot publishedNot published
Where it runs (differs)On your machine (mcp/amazon-bedrock-agentcore-mcp-server)On your machine (@playwright/mcp)
Transportstdiostdio
Tools it declares (differs)12223
Environment variables it asks forNot publishedNot published
Parts of the bundle (differs)Not a bundle1
Licence (differs)Apache-2.0MIT
Repository (differs)github.com/awslabs/mcpgithub.com/microsoft/playwright-mcp
Changes in the last 7 days00
First seen2026-10-112026-10-11

Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.

What each says it does

AWS Bedrock AgentCore

In its own words, on Docker MCP Catalog:

Documentation on AgentCore platform services.

io.github.microsoft/playwright-mcp

In its own words, on Official MCP Registry:

Playwright Tools for MCP

How to run each

AWS Bedrock AgentCore As a local MCP server: Docker image

Claude Code
claude mcp add --transport stdio amazon-bedrock-agentcore -- docker run -i --rm mcp/amazon-bedrock-agentcore-mcp-server

io.github.microsoft/playwright-mcp As a local MCP server: npm package

Claude Code
claude mcp add --transport stdio playwright-mcp -- npx -y @playwright/mcp

Commands built only from what the marketplaces declare; the full set for every client is on each card.

Tools each declares

Only AWS Bedrock AgentCore declares

  • browser_mouse_wheel
  • browser_navigate_forward
  • browser_upload_file
  • create_agent_runtime
  • create_agent_runtime_endpoint
  • delete_agent_runtime
  • delete_agent_runtime_endpoint
  • download_file
  • execute_code
  • execute_command
  • fetch_agentcore_doc
  • gateway_create
Show the remaining 92
  • gateway_delete
  • gateway_get
  • gateway_list
  • gateway_resource_policy_delete
  • gateway_resource_policy_get
  • gateway_resource_policy_put
  • gateway_target_create
  • gateway_target_delete
  • gateway_target_get
  • gateway_target_list
  • gateway_target_synchronize
  • gateway_target_update
  • gateway_update
  • get_agent_runtime
  • get_agent_runtime_endpoint
  • get_browser_session
  • get_code_interpreter_session
  • get_gateway_guide
  • get_identity_guide
  • get_memory_guide
  • get_policy_guide
  • get_runtime_guide
  • identity_create_api_key_provider
  • identity_create_oauth2_provider
  • identity_create_workload_identity
  • identity_delete_api_key_provider
  • identity_delete_oauth2_provider
  • identity_delete_resource_policy
  • identity_delete_workload_identity
  • identity_get_api_key_provider
  • identity_get_oauth2_provider
  • identity_get_resource_policy
  • identity_get_token_vault
  • identity_get_workload_identity
  • identity_list_api_key_providers
  • identity_list_oauth2_providers
  • identity_list_workload_identities
  • identity_put_resource_policy
  • identity_set_token_vault_cmk
  • identity_update_api_key_provider
  • identity_update_oauth2_provider
  • identity_update_workload_identity
  • install_packages
  • invoke_agent_runtime
  • list_agent_runtime_endpoints
  • list_agent_runtime_versions
  • list_agent_runtimes
  • list_browser_sessions
  • list_code_interpreter_sessions
  • memory_batch_create_records
  • memory_batch_delete_records
  • memory_batch_update_records
  • memory_create
  • memory_create_event
  • memory_delete
  • memory_delete_event
  • memory_delete_record
  • memory_get
  • memory_get_event
  • memory_get_record
  • memory_list
  • memory_list_actors
  • memory_list_events
  • memory_list_extraction_jobs
  • memory_list_records
  • memory_list_sessions
  • memory_retrieve_records
  • memory_start_extraction_job
  • memory_update
  • policy_create
  • policy_delete
  • policy_engine_create
  • policy_engine_delete
  • policy_engine_get
  • policy_engine_list
  • policy_engine_update
  • policy_generation_get
  • policy_generation_list
  • policy_generation_list_assets
  • policy_generation_start
  • policy_get
  • policy_list
  • policy_update
  • search_agentcore_docs
  • start_browser_session
  • start_code_interpreter_session
  • stop_browser_session
  • stop_code_interpreter_session
  • stop_runtime_session
  • update_agent_runtime
  • update_agent_runtime_endpoint
  • upload_file

Only io.github.microsoft/playwright-mcp declares

  • browser_drag
  • browser_drop
  • browser_file_upload
  • browser_network_request
  • browser_run_code_unsafe

Both declare

  • browser_click
  • browser_close
  • browser_console_messages
  • browser_evaluate
  • browser_fill_form
  • browser_handle_dialog
  • browser_hover
  • browser_navigate
  • browser_navigate_back
  • browser_network_requests
  • browser_press_key
  • browser_resize
Show the remaining 6
  • browser_select_option
  • browser_snapshot
  • browser_tabs
  • browser_take_screenshot
  • browser_type
  • browser_wait_for

Tool names as each marketplace publishes them. More tools is not better in itself: compare what each needs for the job.

Settings each asks for

Neither one's marketplaces publish the settings it asks for.

What it can do: AWS Bedrock AgentCore · What it can do: io.github.microsoft/playwright-mcp · Compare two other plugins

Data comes from the Docker MCP Catalog (desktop.docker.com/mcp/catalog) and Docker Hub. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-official/blob/HEAD/.claude-plugin/marketplace.json. Data comes from the public marketplace file https://github.com/cursor/plugins/blob/HEAD/.cursor-plugin/marketplace.json. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built