Bowmark: Live Web Data & Browser Actions
Description
Browser automation for AI agents that returns the answer, not a screenshot: live prices, stock and availability, search results, quotes, fares, bookings, and data behind a form or a login. An MCP server that runs the real task on the real website and extracts structured data from the live page, with no browser to drive and no API keys. Search a site, price a product, drive a configurator, start a booking. Covers flights, hotels, car hire, PC parts and insurance across sites including Kayak, Google Flights, Newegg, Micro Center, B&H Photo, Marriott and Hilton. Call get_library for the typed function library, then run a short JavaScript script written against it. Free tier, no signup.
What our measurements say
Bowmark: Live Web Data & Browser Actions is a remote MCP server published at api.bowmark.ai. It has been probed 7 times since 9/10/2026. It answered in 7 of them (100.0%), a near-uninterrupted record. Median response time is 640 ms, a delay an agent will notice. It offers a narrow, focused set of 4 tools. On the protocol side it still runs 2025-11-25 and has not moved to the newer spec.
Agent readability score
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
Agent readability score
Strengths
- Tools have distinct purposes (capability check, execution, account creation, feedback).
- Register tool explicitly documents optional parameters.
Weaknesses
- Tool names are vague (e.g., 'get_library' instead of 'check_capability').
- Descriptions lack specific use cases for some tools.
- Parameter schemas and error handling details are missing.
get_library— Name doesn't clearly indicate capability checking purposerun— Generic name with unclear parameter requirementsregister— No parameter schema details despite being optionalreport— No explicit error handling documentation
Verdict
Event narrative
Risk: medium
- 2026-09-10T21:16:35.016Z — era changed from auth-gated to legacy · system moved to legacy operational mode
- 2026-09-11T01:59:45.474Z — complianceScore set to 100 · security compliance achieved maximum score
- 2026-09-11T03:50:39.090Z — smokeOk changed from null to true · basic system health checks now passing
Advice
Schema compliance
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
- tools/list schema valid
- inputSchema is valid JSON Schema
- Smoke test passed · last run:
- Cold-start: cold 227ms → warm 221ms (penalty 6ms)
Availability history
Event log
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
- Server build: 8.111.3 → 8.112.0
- Server build: 8.111.1 → 8.111.3
- Server build: 8.111.0 → 8.111.1
- Server build: — → 8.111.0
- Supported versions: — → 2025-11-25
- Era changed: Auth-gated → Legacy
- Added to watch — era: Auth-gated
Get your badge
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/bowmark-ai-bowmark)<a href="https://mcpmetrics.io/servers/bowmark-ai-bowmark"><img src="https://mcpmetrics.io/badge/bowmark-ai/bowmark/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to see