A side-by-side look at the AllMCPs Server and Agent Droid Bridge MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose AllMCPs Server for aggregators work over a hosted endpoint; choose Agent Droid Bridge for os automation as a local process. You can also run both side by side in one block.
mcpServersALLMCPS_MCP_URL.search_mcp_servers, get_mcp_install_config, recommend_mcp_stack.ADB_EXECUTION_MODE, ADB_ALLOW_SHELL, ADB_PATH, ADB_EXTRA_TOOL_PACKS, MCP_LOG_ENABLED, MCP_LOG_DIR.get_ui_hierarchy, tap_screen, swipe_screen.Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Aggregators | OS Automation |
| Quality signal | 85/100 · Excellent | 57/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Remote HTTP/SSE | Local subprocess (stdio) |
| Auth | No auth required | No auth required |
| Pricing | Free | Free |
| Required env vars | ALLMCPS_MCP_URL | ADB_EXECUTION_MODEADB_ALLOW_SHELLADB_PATHADB_EXTRA_TOOL_PACKSMCP_LOG_ENABLEDMCP_LOG_DIR |
| Verified owner | Verified | Community listing |
| GitHub stars | 4 | 22 |
| Directory activity | 59 views 20 installs 1 upvotes | 3 views 0 installs 0 upvotes |
| Tools | 11 | 14 |
| Full listing | View AllMCPs Server | View Agent Droid Bridge |
search_mcp_serversSearch the AllMCPs directory for Model Context Protocol (MCP) servers by keyword or category.get_mcp_install_configGet the exact claude_desktop_config.json setup snippet and documentation for a specific MCP server by ID.recommend_mcp_stackRecommend a curated multi-tool MCP server stack for a specific developer role or workflow (e.g. "fullstack", "data science", "devops").list_mcp_categoriesList all categories available in the AllMCPs directory along with server counts.get_boost_pricingGet pricing and features for boosting / featuring an MCP server on AllMCPs.com.boost_mcp_serverInitiate a sponsorship / boost order for an MCP server by ID, returning a Stripe checkout session URL and x402 invoice.get_boost_statusCheck current boost status, verified badge level, and sponsorship expiration for an MCP server by ID.submit_mcp_serverProgrammatically submit a new MCP server repository to AllMCPs.com for indexing and review. Supports the same optional enrichment fields as the human submission form — fill in whichever you can confidently determine from the repository (README, package.json, code) to produce a fully flushed-out listing. Omit anything you are not confident about rather than guessing; all enrichment fields are optional and unrecognized enum values are simply dropped, not rejected.verify_mcp_claimVerify ownership and claim an MCP server listing by checking GitHub README badge, website badge, or DNS TXT record. Works two ways: (1) fully unattended — pass `agentToken` from confirm_mcp_agent (or set an `Authorization: Bearer <token>` header if your client supports it), no human sign-in needed; or (2) if called with neither, requires the caller to already have an active AllMCPs browser session. Unattended agents should use register_mcp_agent + confirm_mcp_agent first.register_mcp_agentStart unattended-agent registration: emails a 6-digit confirmation code to the given address. Follow up with confirm_mcp_agent to exchange the code for a bearer token, which unlocks verify_mcp_claim (and future privileged tools) without ever needing a human to sign in via browser.confirm_mcp_agentExchange the 6-digit code emailed by register_mcp_agent for a durable bearer token (90-day TTL). Pass the returned token as `agentToken` on verify_mcp_claim, or set it as an `Authorization: Bearer <token>` header on subsequent MCP requests if your client supports that.get_ui_hierarchyReturns the current Android screen as an XML UI hierarchy.
Use this when you need to locate element coordinates, read text, or find resource IDs to
interact with. Do not call this after every action — only call it when you actually need to
read screen content. To check if the screen changed after an action, use snapshot_ui before
the action and detect_ui_change after.tap_screenA tap gesture at the given pixel coordinates on the Android screen.swipe_screenA swipe gesture on the Android screen from (x1,y1) to (x2,y2) over the given duration.type_textText input into the currently focused Android input field.
Spaces are encoded automatically.press_keyA key event sent to the Android device using the given keycode integer.take_screenshotA PNG screenshot of the current Android device screen with width, height,
and base64-encoded image data.list_devicesAll Android devices currently visible to ADB, with their serial numbers,
connection state, and model names.launch_appAn Android app launched by its component name (package/activity).execute_adb_commandThe output of an ADB command. Parsed safely via shlex and never passed to a system shell.snapshot_uiTakes a lightweight snapshot of the current UI state and returns a short token.
Use this before performing an action (tap, swipe, launch, key press) when you only need to
confirm the screen changed afterward — not read its content. Pass the returned token to
detect_ui_change as baseline_token. This avoids loading the full XML hierarchy into context
unnecessarily. Do not use this when you need to read or interact with screen elements — use
get_ui_hierarchy for that.detect_ui_changePolls the UI hierarchy after an action and returns when the screen content changes or the
timeout is reached. Returns changed status and elapsed time. By default, omits the XML
hierarchy for efficiency — set return_hierarchy=True to receive the full hierarchy.
For efficient change detection: call snapshot_ui before the action, perform the action, then
call detect_ui_change with baseline_token. Only use without baseline_token when you need to
wait for a slow transition (loading screens, animations). Do not use to read the current
screen state — use get_ui_hierarchy for that.Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
{
"mcpServers": {
"allmcps-server": {
"command": "npx",
"args": [
"-y",
"allmcps-server"
],
"env": {
"ALLMCPS_MCP_URL": "YOUR_ALLMCPS_MCP_URL_HERE"
}
}
}
}
{
"mcpServers": {
"neverlow512-agent-droid-bridge": {
"command": "uvx",
"args": [
"agent-droid-bridge"
],
"env": {
"ADB_EXECUTION_MODE": "YOUR_ADB_EXECUTION_MODE_HERE",
"ADB_ALLOW_SHELL": "YOUR_ADB_ALLOW_SHELL_HERE",
"ADB_PATH": "YOUR_ADB_PATH_HERE",
"ADB_EXTRA_TOOL_PACKS": "YOUR_ADB_EXTRA_TOOL_PACKS_HERE",
"MCP_LOG_ENABLED": "YOUR_MCP_LOG_ENABLED_HERE",
"MCP_LOG_DIR": "YOUR_MCP_LOG_DIR_HERE"
}
}
}
}
get_screen_elementsStructured list of UI elements currently visible on the Android screen.
Returns elements filtered and shaped by the chosen mode. Prefer 'tappable' for
navigation and 'interactive' when you need XPath or bounds for ADB commands.
Only use 'all' as a last resort — it returns every node and can be large.