{"id":"qoxogus-spring-ai-chrome-mcp-server","name":"spring-ai-chrome-mcp-server","homepage":null,"repo_url":"https://github.com/qoxogus/spring-ai-chrome-mcp-server","category":"devtools","subcategories":[],"tags":["mcp","browser-automation","chrome","web-interaction","agent-tools","screenshot","text-extraction"],"what_it_does":"Provides an MCP server that allows an AI agent to control a Chrome browser instance and perform web-browsing actions (open browser/tabs, navigate, click links, input text, extract page text, take screenshots, manage cookies).","use_cases":["Automated research workflows that require interacting with live web pages","Testing/validation of UI flows via scripted browser interactions","Summarizing content from pages after navigation/search","Collecting page metadata (title, text, screenshots) for downstream processing"],"not_for":["Highly sensitive tasks where handling private credentials/cookies is required without strong isolation","Use in untrusted browsing contexts without sandboxing","Production systems needing strict reliability guarantees or documented operational guarantees"],"best_when":"You need agent-driven, interactive browser actions and you can run the MCP server locally/in a controlled environment.","avoid_when":"You need formal auth, strict rate-limit controls, or comprehensive operational/error-contract documentation.","alternatives":["Playwright/Selenium driven directly from your agent/runtime","Browserless/automation SaaS (if you require managed infrastructure)","Headless scraping tools for static content (where JS execution is unnecessary)"],"af_score":52.0,"security_score":15.0,"reliability_score":27.5,"package_type":"mcp_server","discovery_source":["github"],"priority":"low","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-04-04T19:49:37.333019+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":[],"oauth":false,"scopes":false,"notes":"No authentication mechanism is described in the provided README; MCP is configured via local stdio command args."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":null},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":52.0,"security_score":15.0,"reliability_score":27.5,"mcp_server_quality":60.0,"documentation_accuracy":55.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":90.0,"rate_limit_clarity":0.0,"tls_enforcement":0.0,"auth_strength":10.0,"scope_granularity":0.0,"dependency_hygiene":30.0,"secret_handling":40.0,"security_notes":"The README indicates browser/cookie operations but does not describe authentication, sandboxing, or secret/cookie isolation. MCP is run via local stdio (no TLS/auth controls described), so security depends on deployment environment. Risk of handling sensitive cookies/PII and of unsafe web content interaction if not sandboxed.","uptime_documented":0.0,"version_stability":40.0,"breaking_changes_history":50.0,"error_recovery":20.0,"idempotency_support":"false","idempotency_notes":"Many tools are inherently stateful (open/close tabs, navigate, click). No idempotency guidance is provided.","pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["State management matters: browsers are tracked by browser ID and tabs by index; the agent must track and pass the correct IDs/indices.","Navigation/click actions depend on page load timing; without explicit waits (not documented), actions may fail or operate on the wrong page state.","Cookie/session handling may persist across operations unless explicitly cleared; agents should be careful about cross-task contamination."]}}