Browserless
Server Details
Browserless MCP — wraps the Browserless headless-Chromium REST API (browserless.io)
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 0.2% over 38 days
- Last Tested
- Transport
- Streamable HTTP
- URL
- Repository
- pipeworx-io/mcp-browserless
- GitHub Stars
- 0
- Server Listing
- browserless
TDQS
Scored across 44 tools
The set spans many domains with distinct leaves, but the ask_pipeworx family (ask_pipeworx, _beta, _grounded, deep_research) and the Polymarket suite (polymarket_edges, _arbitrage, _fill_risk, _kalshi_spread) overlap enough that agents can misselect without reading lengthy descriptions. Memory, subscription, and browserless tools are clearly separable, but several meta and research tools have fuzzy boundaries.
All names use snake_case without camelCase mixing; most are readable resource_action or action_noun. However the convention is not uniformly verb_noun—many are noun phrases (company_facts, recent_alerts, polymarket_edges) and some have vendor prefixes—so consistency is good but not perfect.
44 tools is far beyond the 3-15 well-scoped range and exceeds the 25+ too-many threshold; the catalog tries to cover browser rendering, finance, prediction markets, memory, subscriptions, and meta-routing in one surface. The breadth may be intentional for a data platform, but the tool count is excessive for most agents.
The surface covers many workflows (subscriptions lifecycle, memory, Polymarket analysis, entity/financial lookups) but is patchy: some domains are reachable only through meta-routing, and direct operations like browser PDF generation, update/delete for many resources, or direct economic data lookup are absent. The meta-tools partially compensate, but obvious gaps remain.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
7 tool updates
- Added
archive_compare - Added
archive_evidence - Changed
ask_pipeworx1 field changed- added
Input schema / properties / packsAdded value: +{ + "description": "OPTIONAL. Restrict routing to these pack slugs (e.g. [\"sec-form-d\",\"sec-13f\"]) — the router then picks only from tools in those packs. Omit for the default full-catalog routing. Slugs come from list_packs / search_packs / https://pipeworx.io/directory; unlisted or unknown slugs are ignored and named in _meta.pack_scope.ignored, and if none of them resolves the question is routed across the whole catalog with _meta.pack_scope.full_catalog:true (never an empty answer).", + "items": { + "type": "string" + }, + "type": "array" +}
- Changed
ask_pipeworx_beta1 field changed- added
Input schema / properties / packsAdded value: +{ + "description": "OPTIONAL. Restrict routing to these pack slugs (e.g. [\"sec-form-d\",\"sec-13f\"]) — the router then picks only from tools in those packs. Omit for the default full-catalog routing. Slugs come from list_packs / search_packs / https://pipeworx.io/directory; unlisted or unknown slugs are ignored and named in _meta.pack_scope.ignored, and if none of them resolves the question is routed across the whole catalog with _meta.pack_scope.full_catalog:true (never an empty answer).", + "items": { + "type": "string" + }, + "type": "array" +}
- Added
classify_row - Added
research_row - Changed
subscribe2 fields changed- changed
Input schema / properties / params / descriptionPrevious value: -"Type-specific filter. sec_8k: {ticker:\"AAPL\", items?:[\"5.02\",\"1.01\"]}. polymarket_edge: {topic:\"fed\", min_spread_bps?:500}. fred_series: {series_id:\"UNRATE\"}. patent_grant: {applicant:\"Apple Inc.\"}. clinical_trial: {sponsor?:\"Pfizer\", condition?:\"lung cancer\", phase?:\"PHASE3\"} (sponsor or condition required)."New value: +"Type-specific filter. sec_8k: {ticker:\"AAPL\", items?:[\"5.02\",\"1.01\"]}. polymarket_edge: {topic:\"fed\", min_spread_bps?:500}. fred_series: {series_id:\"UNRATE\"}. patent_grant: {applicant:\"Apple Inc.\"}. clinical_trial: {sponsor?:\"Pfizer\", condition?:\"lung cancer\", phase?:\"PHASE3\"} (sponsor or condition required). form_d: {state?:\"CA\", industry?:\"Biotechnology\", min_amount?:500000, exemption?:\"06B\"} (all optional — omit all to watch every new Form D nationwide). news_keyword: {query:\"\\\"semiconductor sanctions\\\"\", lang?:\"eng\", domains?:[\"reuters.com\"]} (query required). job_post: EITHER {ats:\"greenhouse\", board_token:\"acme\"} (exact board) OR {domain:\"acme.com\"} (auto-detected), plus optional title_query/location_query substrings. tool_diff: {tool:\"form5500\", args?:{...}, fields:[\"headcount\"], schedule:\"daily\"} — re-runs that tool on schedule and fires when the named fields change; tool must be read-only and not need a Pipeworx-held platform key; schedule \"hourly\" needs the paid tier. new_entity: {state:\"CO\", name_query?:\"dental\", entity_type?:\"limited liability\"} — state is required and must be one of FL, NY, CO, OR, CT, TX, PA. Unknown keys in form_d/news_keyword/job_post/tool_diff/new_entity params are rejected at subscribe time." - changed
Input schema / properties / type / enumPrevious value: -[ - "sec_8k", - "polymarket_edge", - "fred_series", - "patent_grant", - "clinical_trial" -]New value: +[ + "sec_8k", + "polymarket_edge", + "fred_series", + "patent_grant", + "clinical_trial", + "form_d", + "news_keyword", + "job_post", + "tool_diff", + "new_entity" +]
1 tool update
- Changed
release_calendar_markets2 fields changed- added
Output schema / properties / empty_reasonAdded value: +{ + "description": "Present ONLY on a zero-release window: \"no_releases_in_window\". The window was queried and nothing is scheduled — this is an answer, not a failure.", + "type": "string" +} - added
Output schema / properties / hintAdded value: +{ + "description": "Present ONLY on a zero-release window: what to change (usually a wider `hours`).", + "type": "string" +}
40 tool updates
- First observed
ai_visibility_check - First observed
ask_pipeworx - First observed
ask_pipeworx_beta - First observed
ask_pipeworx_grounded - First observed
bet_research - First observed
browserless_content - First observed
browserless_scrape - First observed
browserless_screenshot - First observed
browserless_smart_scrape - First observed
company_facts - First observed
compare_entities - First observed
deep_research - First observed
discover_tools - First observed
entity_profile - First observed
forget - First observed
generate_llms_txt - First observed
kalshi_weather_edge - First observed
list_subscriptions - First observed
pipeworx_feedback - First observed
pipeworx_trending - First observed
polymarket_arbitrage - First observed
polymarket_edge_tracker - First observed
polymarket_edges - First observed
polymarket_fill_risk - First observed
polymarket_kalshi_spread - First observed
recall - First observed
recent_alerts - First observed
recent_changes - First observed
release_calendar_markets - First observed
remember - First observed
resolution_audit - First observed
resolution_diff - First observed
resolve_entity - First observed
scan_competitor_ai_presence - First observed
scan_dependency - First observed
search_within - First observed
subscribe - First observed
suggest_questions - First observed
unsubscribe - First observed
validate_claim
Related MCP Connectors
Official Browserless MCP server: browser automation, scraping, screenshots and PDFs for AI agents.
ScrapingBee MCP — wraps the ScrapingBee headless-scraping API (scrapingbee.com)
Crawlbase MCP — wraps the Crawlbase Crawling API (crawlbase.com, formerly ProxyCrawl). One…
Scrapingdog MCP — wraps Scrapingdog (scrapingdog.com), a proxy-based web
Related MCP Servers
AlicenseAqualityAmaintenanceMCP server for Browserless.io: scrape and automate any site, bypass captchas and enable stealth mode171,833 npm8Server Side Public , v 1- FlicenseNot gradedqualityCmaintenanceHeadless browser automation for LLM agents via REST API or MCP tools. Enables navigating pages, reading structured content, clicking elements, filling forms, and executing JavaScript.-
- FlicenseNot gradedqualityBmaintenanceEnables MCP clients to remotely control a headless Chromium browser via Playwright, including navigation, clicking, typing, form filling, screenshots, and network request monitoring, over Streamable HTTP and deployable to Azure Container Apps.-
- AlicenseBqualityDmaintenanceAn MCP server for generic browser automation using Playwright. Enables MCP clients to navigate pages, inspect elements, execute JavaScript, capture screenshots, and monitor console logs and network traffic via a headless Chromium instance.76 npmISC
Glama MCP Gateway
Add one secure layer between your agents and this server.