Install
openclaw skills install slbrow-skillBrowser automation via SLBrow MCP and HTTP API. Use when the user needs to navigate pages, analyze content, manage tabs, search history, extract text, or control the browser. Supports both MCP tools and direct curl commands. Requires SLBrow server running and browser extension installed.
openclaw skills install slbrow-skillSkills for browser-side AI assistant. The browser plugin (aiassist) connects to slbrow-mcp via MCP protocol; these skills guide when and how to use the tools. Can be used via MCP tools or direct HTTP API calls with curl.
npx slbrow or npm start in ai/slbrowmcp/slbrow-mcp/http://127.0.0.1:5556/mcp (视联浏览器MCP), http://127.0.0.1:5556/vaimcp (视联视频AI MCP)When the MCP plugin is enabled, the AI has access to browser tools. Use these skills to guide tool selection and workflow:
page_navigate to open URLspage_analyze with intent_hint (article, form submit, post_create) before extractiontab_list first, then pass tab_id to target specific tabsAlways available - Use curl commands to control browser directly without MCP plugin dependency:
Basic format (PowerShell-friendly — no temp JSON file):
curl.exe -X POST http://localhost:5556/api/execute -H 'Content-Type: application/json' -d '{\"tool\":\"TOOL_NAME\",\"args\":{\"PARAM\":\"VALUE\"}}'
Important notes for Windows PowerShell:
curl.exe instead of curl (PowerShell aliases curl to Invoke-WebRequest)-d '...' with single quotes around the whole argument; backslash-escape every double quote in the JSON (\"). That way the shell passes valid JSON to curl without needing --data-binary @fileCommon curl examples:
# Create new tab and navigate
curl.exe -X POST http://localhost:5556/api/execute -H 'Content-Type: application/json' -d '{\"tool\":\"tab_create\",\"args\":{\"url\":\"https://www.163.com\"}}'
# Navigate current tab
curl.exe -X POST http://localhost:5556/api/execute -H 'Content-Type: application/json' -d '{\"tool\":\"page_navigate\",\"args\":{\"url\":\"https://www.example.com\"}}'
# List all tabs
curl.exe -X POST http://localhost:5556/api/execute -H 'Content-Type: application/json' -d '{\"tool\":\"tab_list\",\"args\":{}}'
# Analyze page content
curl.exe -X POST http://localhost:5556/api/execute -H 'Content-Type: application/json' -d '{\"tool\":\"page_analyze\",\"args\":{\"intent_hint\":\"article\"}}'
# Extract article content
curl.exe -X POST http://localhost:5556/api/execute -H 'Content-Type: application/json' -d '{\"tool\":\"page_extract_content\",\"args\":{\"content_type\":\"article\"}}'
# Close specific tab
curl.exe -X POST http://localhost:5556/api/execute -H 'Content-Type: application/json' -d '{\"tool\":\"tab_close\",\"args\":{\"tab_id\":1234567890}}'
# Search browser history
curl.exe -X POST http://localhost:5556/api/execute -H 'Content-Type: application/json' -d '{\"tool\":\"get_history\",\"args\":{\"keywords\":\"search term\",\"max_results\":10}}'
Response format:
API returns JSON with success, tool, result, and formatted fields for easy parsing.
| Tool | Description |
|---|---|
page_navigate | Navigate current tab to URL |
page_analyze | Analyze page for elements (intent_hint: article, form submit, post_create, etc.) |
page_extract_content | Extract content (content_type: article, search_results, posts) |
page_wait_for | Wait for element or text (condition_type, selector, text) |
tab_create | Create tab(s) (url, urls[], or count) |
tab_close | Close tab(s) (tab_id, tab_ids[]) |
tab_list | List open tabs with IDs |
get_history | Search browser history (keywords, start_date, end_date, domains, max_results) |
get_selected_text | Get selected text (optional tab_id) |
get_page_links | Get page links (link_type: all/internal/external, domains, max_results) |
| Tool | Description |
|---|---|
get_page_seelink_player_list | Get all players on current page |
use_seelink_players_ai | Apply AI function to players (ai_function_name: reduce_fog, face_mosaic, dark_reduce, human_outline, vechicle_outline, none) |
Multi-tab workflow:
tab_list to get tab IDstab_id to any tool to target a background tabContent extraction:
page_navigate to target URLpage_analyze with intent_hint to find elementspage_extract_content for article/search_results/postsForm filling:
page_analyze with intent_hint "form submit" to discover form elementspage_analyze or page_extract_content to confirm stateVAI (Seelink player AI):
get_page_seelink_player_list to get player IDs and countplayer_position_list (zero-based index) or player_id_list (not both)use_seelink_players_ai with chosen targets and ai_function_nameuse_seelink_players_ai separately for eachai_function_name to "none"The browser plugin can fetch skills from the server to inject into AI context:
GET http://127.0.0.1:5556/api/skills
Returns the full SKILL.md content (text/markdown). Use when slbrow MCP plugins are enabled to guide tool usage.
For full parameter schemas, see references/api-reference.md.
EXTENSION_DISCONNECTED: Ensure extension is installed and server is running. Check http://localhost:5556/health first.Tool call timeout: Operation took >30s; retry with simpler args or break into smaller steps.page_analyze returns 0 elements: Page may still be loading — wait a moment and retry, or page_navigate again.tab_id invalid (tab was closed): Call tab_list to refresh available tab IDs before retrying.Tab Management:
tab_create with url parametertab_list with empty argstab_close with tab_id parameterpage_navigate with url parameterContent Analysis:
page_analyze with intent_hint (article, form_submit, post_create)page_extract_content with content_type (article, search_results, posts)get_page_links with link_type (all, internal, external)History & Text:
get_history with keywords, max_resultsget_selected_text with optional tab_idSeelink AI:
get_page_seelink_player_listuse_seelink_players_ai with player_position_list or player_id_list and ai_function_nameServer not responding:
curl.exe http://localhost:5556/healthnpx slbrow or npm startCurl command fails:
curl.exe in PowerShell-d, use single-quoted JSON with \" around each JSON string delimiter (see Method 2 examples above)Tab operations not working:
tab_list to get current tab IDs first