{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"github-xpzouying--xiaohongshu-mcp","slug":"xpzouying--xiaohongshu-mcp","name":"xiaohongshu-mcp","type":"mcp","url":"https://www.haha.ai/xiaohongshu-mcp","page_url":"https://unfragile.ai/xpzouying--xiaohongshu-mcp","categories":["mcp-servers"],"tags":["mcp","mcp-server","xiaohongshu-mcp"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"github-xpzouying--xiaohongshu-mcp__cap_0","uri":"capability://tool.use.integration.mcp.protocol.exposure.of.xiaohongshu.platform.operations","name":"mcp protocol exposure of xiaohongshu platform operations","description":"Exposes Xiaohongshu social platform capabilities as a set of 13 standardized MCP tools consumable by AI clients (Claude, Cursor, Gemini CLI, Cline, VSCode). The service implements the Model Context Protocol specification on a /mcp endpoint with streamable HTTP transport, translating MCP tool calls into internal service method invocations. Each tool is registered in mcp_server.go with JSON schema definitions and dispatched through mcp_handlers.go to the underlying XiaohongshuService layer.","intents":["Enable Claude or other AI assistants to programmatically interact with Xiaohongshu without writing custom integrations","Expose Xiaohongshu operations as discoverable tools within an AI agent's context","Allow MCP-compatible clients to call Xiaohongshu actions with standardized tool invocation semantics"],"best_for":["AI agent builders integrating Xiaohongshu automation into Claude or Cursor workflows","Teams building multi-platform social media automation using MCP as the integration standard"],"limitations":["MCP protocol adds ~50-100ms overhead per tool call due to JSON serialization and HTTP round-trip","Tool discovery and schema validation happens on every client connection — no caching of tool definitions","Streaming responses for large result sets (e.g., feed retrieval) may buffer in memory before transmission"],"requires":["MCP-compatible client (Claude, Cursor, Gemini CLI, Cline, or VSCode with MCP extension)","xiaohongshu-mcp service running on port 18060","Valid Xiaohongshu session cookies (from prior xiaohongshu-login execution)"],"input_types":["JSON-encoded MCP tool call requests with typed parameters"],"output_types":["JSON-encoded MCP tool result responses with structured data or error messages"],"categories":["tool-use-integration","mcp-protocol"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-xpzouying--xiaohongshu-mcp__cap_1","uri":"capability://automation.workflow.headless.browser.based.session.authentication.with.qr.code.flow","name":"headless browser-based session authentication with qr code flow","description":"Implements a two-phase authentication system: xiaohongshu-login binary handles interactive QR code scanning via headless Chrome, persisting authenticated session cookies to cookies.json; the main xiaohongshu-mcp service reads these cookies on startup and injects them into every subsequent browser session opened via go-rod/rod. This approach bypasses the need for API credentials by reusing the user's authenticated browser context across all platform operations.","intents":["Authenticate with Xiaohongshu without exposing username/password or API keys","Maintain persistent session state across multiple service restarts and tool invocations","Enable operators to authenticate once and run the service unattended for extended periods"],"best_for":["Operators deploying xiaohongshu-mcp in headless environments (servers, containers, CI/CD)","Teams requiring session persistence without storing plaintext credentials"],"limitations":["QR code authentication requires interactive terminal access during initial setup — cannot be fully automated","Session cookies may expire after 30-90 days depending on Xiaohongshu's session policy; requires periodic re-authentication","Cookies stored in plaintext JSON file (cookies.json) — no encryption at rest; file permissions must be restricted manually","Browser automation adds 2-5 second latency per operation due to Chrome startup and page load times"],"requires":["Go 1.18+ (for building xiaohongshu-login binary)","Headless Chrome or Chromium installed on the system","go-rod/rod library (included in go.mod)","Interactive terminal access for initial QR code scan"],"input_types":["QR code image (displayed in terminal during login)","User's phone camera scan of QR code"],"output_types":["cookies.json file containing session cookies and authentication tokens"],"categories":["automation-workflow","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-xpzouying--xiaohongshu-mcp__cap_10","uri":"capability://automation.workflow.browser.session.pooling.and.lifecycle.management","name":"browser session pooling and lifecycle management","description":"Manages headless Chrome browser instances through go-rod/rod, implementing session pooling to reuse browser contexts across multiple operations. The service opens a browser instance on startup, injects authenticated cookies into each session, and reuses the browser for subsequent tool invocations. Browser lifecycle is tied to the service lifecycle — the browser is closed when the service shuts down. This approach reduces startup latency compared to opening a new browser for each operation.","intents":["Reduce latency for sequential operations by reusing browser instances","Maintain authenticated browser context across multiple tool invocations","Manage browser resource consumption by pooling instances rather than spawning new browsers"],"best_for":["High-frequency automation workflows where latency is critical","Long-running services that execute many sequential operations","Resource-constrained environments (e.g., containers, serverless) where browser startup overhead is significant"],"limitations":["Browser pooling adds complexity to session management — must handle browser crashes and reconnection","Shared browser context may leak state between operations — operations may interfere with each other if not properly isolated","Browser memory usage grows over time as pages are loaded and cached — no automatic garbage collection or memory limit","Browser crashes are not automatically recovered — service must be restarted to recover from browser failures","Concurrent operations on the same browser instance may cause race conditions or DOM conflicts"],"requires":["Headless Chrome or Chromium installed on the system","go-rod/rod library (included in go.mod)","Sufficient memory to keep browser instance running (typically 100-500MB per browser)"],"input_types":["none (browser pooling is transparent to clients)"],"output_types":["none (browser pooling is transparent to clients)"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-xpzouying--xiaohongshu-mcp__cap_11","uri":"capability://data.processing.analysis.dom.based.data.extraction.and.parsing.with.brittle.resilience","name":"dom-based data extraction and parsing with brittle resilience","description":"Extracts post metadata, user information, and engagement metrics by parsing the Xiaohongshu DOM through go-rod/rod's element selection and text extraction APIs. The service uses CSS selectors and XPath queries to locate elements, extract text content, and construct structured data objects. This approach enables operation without reverse-engineering proprietary APIs, but is brittle to HTML structure changes.","intents":["Extract post metadata (title, author, engagement counts) from Xiaohongshu pages","Parse user profile information and follower counts","Build structured data objects from unstructured HTML for downstream processing"],"best_for":["Automation workflows that need to extract data from Xiaohongshu without API access","Data pipelines that transform unstructured HTML into structured formats","Monitoring tools that track engagement metrics or content changes"],"limitations":["DOM parsing is brittle — changes to Xiaohongshu's HTML structure may break extraction without warning","CSS selectors and XPath queries are hardcoded — no dynamic selector discovery or fallback mechanisms","Extraction latency depends on page load time and DOM complexity — may add 1-3 seconds per operation","No validation or error handling for missing elements — extraction may silently fail or return null values","Extracted data may be incomplete or inaccurate if Xiaohongshu's HTML structure differs from expected format"],"requires":["go-rod/rod library for DOM access","Headless Chrome with JavaScript execution enabled","Knowledge of Xiaohongshu's HTML structure (CSS selectors and XPath queries)"],"input_types":["none (DOM parsing is transparent to clients)"],"output_types":["structured data objects (posts, users, engagement metrics) extracted from DOM"],"categories":["data-processing-analysis","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-xpzouying--xiaohongshu-mcp__cap_12","uri":"capability://tool.use.integration.structured.error.handling.and.response.serialization.across.protocol.boundaries","name":"structured error handling and response serialization across protocol boundaries","description":"Implements consistent error handling and response serialization across MCP and REST interfaces. The service layer returns structured error objects with error codes, messages, and optional context; mcp_handlers.go and handlers_api.go translate these into protocol-specific responses (MCP error format or HTTP status codes). This design ensures that clients receive consistent error information regardless of which interface they use.","intents":["Provide consistent error messages and codes across MCP and REST clients","Enable clients to programmatically handle errors based on error codes","Serialize complex response objects (posts, users, engagement metrics) into protocol-specific formats"],"best_for":["Teams building MCP servers that need to support both MCP and REST clients","Error handling and recovery workflows that depend on consistent error codes","Monitoring and logging systems that need to parse and categorize errors"],"limitations":["Error serialization adds complexity to handlers — must translate between service-level and protocol-specific error formats","MCP and REST may have different error semantics — some errors may not map cleanly between protocols","Error context may be lost during translation — detailed error information may not be preserved across protocol boundaries","No standardized error code taxonomy — error codes are service-specific and may not be portable to other services"],"requires":["Structured error types in service layer (service.go)","Error translation logic in handlers (mcp_handlers.go, handlers_api.go)","HTTP status code mapping for REST errors"],"input_types":["none (error handling is transparent to clients)"],"output_types":["structured error responses with error codes, messages, and context"],"categories":["tool-use-integration","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-xpzouying--xiaohongshu-mcp__cap_13","uri":"capability://automation.workflow.stateless.http.server.with.per.request.browser.session.isolation","name":"stateless http server with per-request browser session isolation","description":"Implements a stateless HTTP server (using Gin framework) where each MCP or REST request opens a fresh browser page/tab within the pooled browser instance, executes the operation, and closes the page. This approach isolates state between requests, preventing cross-request contamination while reusing the browser instance for performance. The server maintains no per-request state — all context is passed through request parameters.","intents":["Execute multiple concurrent or sequential operations without state leakage between requests","Isolate browser DOM state between operations to prevent interference","Scale horizontally by avoiding per-request state that would require session affinity"],"best_for":["High-concurrency environments where multiple clients invoke operations simultaneously","Stateless deployment scenarios (containers, serverless, load-balanced clusters)","Automation workflows that require strict isolation between operations"],"limitations":["Per-request page creation adds 500ms-1s latency per operation due to page load and initialization","Concurrent requests may contend for browser resources — browser may become a bottleneck under high load","No cross-request state sharing — clients cannot maintain session-level context across multiple operations","Browser instance is a single point of failure — if browser crashes, all concurrent requests fail"],"requires":["Gin framework for HTTP routing","go-rod/rod for browser session management","Stateless request handlers that do not rely on global state"],"input_types":["HTTP requests (MCP or REST) with all necessary context in request parameters"],"output_types":["HTTP responses (MCP or REST) with operation results"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-xpzouying--xiaohongshu-mcp__cap_2","uri":"capability://automation.workflow.content.publishing.with.text.images.and.video.support","name":"content publishing with text, images, and video support","description":"Provides two distinct publishing tools: publish_content for text-based posts with optional image attachments, and publish_with_video for video content. Both tools operate through browser automation, constructing the Xiaohongshu post creation form via DOM manipulation and submitting it through the live web interface. The service handles image/video file uploads, caption composition, and hashtag injection before form submission.","intents":["Publish text posts with images to Xiaohongshu programmatically from an AI agent","Upload and publish video content with captions and metadata","Automate content distribution workflows where AI generates captions and selects media"],"best_for":["Content creators automating post scheduling and publishing workflows","AI agents generating and publishing social media content at scale","Teams building multi-platform content distribution pipelines"],"limitations":["Publishing is destructive and rate-limited by Xiaohongshu — no undo capability; failed publishes may leave partial posts","Video publishing requires video file to be pre-encoded and stored locally — no transcoding or format conversion","Image uploads limited to Xiaohongshu's file size and format restrictions (typically <10MB per image, <100MB per video)","Browser automation adds 5-15 second latency per publish operation due to form rendering and submission","No support for scheduled publishing — posts are published immediately upon tool invocation"],"requires":["Valid Xiaohongshu session (authenticated via xiaohongshu-login)","Local file paths to image or video files","Post caption text (required)","Headless Chrome with go-rod/rod driver"],"input_types":["text (post caption)","file paths (image or video files)","structured metadata (hashtags, mentions)"],"output_types":["structured response with post ID, URL, and publication timestamp on success; error details on failure"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-xpzouying--xiaohongshu-mcp__cap_3","uri":"capability://search.retrieval.feed.retrieval.and.pagination.with.cursor.based.navigation","name":"feed retrieval and pagination with cursor-based navigation","description":"Implements get_feed tool that retrieves the authenticated user's Xiaohongshu feed with cursor-based pagination. The service navigates the feed DOM, extracts post metadata (title, author, engagement metrics, timestamps), and returns paginated results. Cursor tokens encode the position in the feed, enabling clients to request subsequent pages without re-fetching earlier content.","intents":["Retrieve the user's personalized Xiaohongshu feed programmatically for analysis or curation","Paginate through feed results without loading the entire feed into memory","Extract post metadata (engagement, author info, timestamps) for downstream processing"],"best_for":["AI agents analyzing user feeds to identify trends or high-engagement content","Content curators building recommendation or discovery workflows","Analytics pipelines extracting engagement metrics from social feeds"],"limitations":["Cursor-based pagination is stateless but opaque — clients cannot predict cursor values or skip to arbitrary positions","Feed content is dynamic and user-personalized — same cursor may return different results on subsequent calls if feed is updated","DOM extraction is brittle — changes to Xiaohongshu's HTML structure may break feed parsing without warning","No filtering or sorting options — feed is returned in Xiaohongshu's default order (typically chronological or algorithmic)"],"requires":["Valid Xiaohongshu session","Headless Chrome with go-rod/rod driver","Network connectivity to Xiaohongshu servers"],"input_types":["optional cursor token (string) for pagination; omit for first page"],"output_types":["structured array of post objects with metadata (title, author, engagement counts, timestamps); next_cursor for pagination"],"categories":["search-retrieval","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-xpzouying--xiaohongshu-mcp__cap_4","uri":"capability://search.retrieval.full.text.search.across.xiaohongshu.posts.with.result.ranking","name":"full-text search across xiaohongshu posts with result ranking","description":"Implements search_posts tool that executes full-text search queries against Xiaohongshu's search index via the web interface. The service submits search queries through the browser, parses ranked search results from the DOM, and returns posts sorted by relevance. Search results include post metadata, author info, and engagement metrics extracted from the search result page.","intents":["Search for specific content, hashtags, or keywords across Xiaohongshu","Discover trending topics or high-engagement posts matching a query","Build recommendation or discovery workflows based on search results"],"best_for":["Content discovery tools and recommendation engines","Trend analysis and social listening workflows","AI agents researching specific topics or hashtags on Xiaohongshu"],"limitations":["Search results are ranked by Xiaohongshu's algorithm — no control over ranking or filtering criteria","Search queries are rate-limited by Xiaohongshu; excessive searches may trigger temporary blocks","DOM parsing is brittle — changes to Xiaohongshu's search result HTML structure may break result extraction","No advanced search operators (e.g., date range, author filters) — only simple keyword queries are supported","Search results may be personalized based on user's history — same query may return different results for different users"],"requires":["Valid Xiaohongshu session","Headless Chrome with go-rod/rod driver","Network connectivity to Xiaohongshu servers"],"input_types":["search query (string, required)","optional pagination cursor for result pages"],"output_types":["structured array of search result objects with post metadata, author info, engagement metrics; next_cursor for pagination"],"categories":["search-retrieval","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-xpzouying--xiaohongshu-mcp__cap_5","uri":"capability://automation.workflow.user.engagement.actions.like.comment.follow.with.idempotency","name":"user engagement actions (like, comment, follow) with idempotency","description":"Provides tools for user engagement: like_post, comment_on_post, and follow_user. Each tool operates through browser automation, simulating user interactions (clicking like buttons, submitting comment forms, following profiles) via DOM manipulation. The service handles engagement state tracking to prevent duplicate actions and returns confirmation of the engagement action.","intents":["Programmatically like or comment on posts as part of engagement workflows","Follow relevant users or accounts to build follower networks","Automate engagement metrics collection and interaction logging"],"best_for":["Social media automation workflows that require user engagement","Community management bots that interact with followers","Growth hacking tools that automate follower acquisition"],"limitations":["Engagement actions are rate-limited by Xiaohongshu — excessive likes/comments may trigger temporary blocks or shadow-bans","Like and follow actions are destructive and not easily reversible — no built-in undo capability","Comment text is submitted as-is without moderation or filtering — clients are responsible for comment quality","Idempotency is best-effort only — if the service crashes between action execution and state recording, duplicate actions may occur","Browser automation adds 2-5 second latency per engagement action due to DOM manipulation and form submission"],"requires":["Valid Xiaohongshu session","Post ID or user ID (depending on action)","Comment text (for comment_on_post)","Headless Chrome with go-rod/rod driver"],"input_types":["post ID (string, for like_post and comment_on_post)","user ID (string, for follow_user)","comment text (string, for comment_on_post)"],"output_types":["structured response with action status (success/failure), timestamp, and engagement state"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-xpzouying--xiaohongshu-mcp__cap_6","uri":"capability://automation.workflow.login.status.checking.and.session.validation","name":"login status checking and session validation","description":"Implements check_login_status tool that validates the current Xiaohongshu session by attempting to access a protected resource (e.g., user profile page) through the browser. The service returns the authentication status, user ID, and username if logged in, or an error if the session is invalid or expired. This tool enables clients to verify session health before executing other operations.","intents":["Verify that the Xiaohongshu session is still valid before executing operations","Detect session expiration and prompt re-authentication","Extract the authenticated user's ID and username for logging or verification"],"best_for":["Service health checks and monitoring workflows","AI agents that need to verify authentication before executing sensitive operations","Deployment scripts that validate session setup before starting the service"],"limitations":["Status check requires a live browser request to Xiaohongshu — adds 2-3 second latency","Session validation is point-in-time only — session may expire immediately after check completes","No detailed error messages for different failure modes (expired vs. invalid vs. network error) — all failures return generic error","Checking status does not refresh or extend session lifetime — expired sessions remain expired"],"requires":["Headless Chrome with go-rod/rod driver","Network connectivity to Xiaohongshu servers"],"input_types":["none (no parameters required)"],"output_types":["structured response with login status (boolean), user ID, username, and session expiration timestamp if available"],"categories":["automation-workflow","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-xpzouying--xiaohongshu-mcp__cap_7","uri":"capability://automation.workflow.qr.code.generation.for.interactive.login","name":"qr code generation for interactive login","description":"Implements get_login_qrcode tool that generates a fresh Xiaohongshu login QR code by opening the login page in a headless browser and extracting the QR code image. The service returns the QR code as a base64-encoded image or file path, enabling operators or AI clients to display it for scanning. This tool is typically used during initial setup or when re-authentication is required.","intents":["Generate a fresh login QR code for interactive authentication","Enable operators to re-authenticate when the session expires","Display QR code in terminal or UI for user scanning"],"best_for":["Initial setup workflows where operators need to authenticate interactively","Re-authentication flows when session cookies expire","Deployment scripts that need to handle authentication interactively"],"limitations":["QR code is time-limited (typically valid for 5-10 minutes) — clients must scan quickly or request a new code","QR code generation requires a live browser request to Xiaohongshu — adds 2-3 second latency","QR code image format and encoding may change with Xiaohongshu updates — brittle to platform changes","No support for alternative authentication methods (username/password, OAuth) — only QR code scanning is supported"],"requires":["Headless Chrome with go-rod/rod driver","Network connectivity to Xiaohongshu servers","Interactive terminal or UI to display QR code for scanning"],"input_types":["none (no parameters required)"],"output_types":["QR code image as base64-encoded string or file path; expiration timestamp"],"categories":["automation-workflow","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-xpzouying--xiaohongshu-mcp__cap_8","uri":"capability://automation.workflow.session.cookie.management.and.deletion","name":"session cookie management and deletion","description":"Implements delete_cookies tool that clears the stored Xiaohongshu session cookies from cookies.json, effectively logging out the authenticated user. This tool is destructive and irreversible — after deletion, the service cannot authenticate with Xiaohongshu until new cookies are obtained via xiaohongshu-login. The tool is useful for cleanup, security, or switching to a different user account.","intents":["Log out the current Xiaohongshu user and clear session state","Switch to a different user account by clearing old cookies","Clean up session state during service shutdown or maintenance"],"best_for":["Service cleanup and shutdown workflows","Multi-user scenarios where different operators need to authenticate with different accounts","Security workflows where session credentials need to be cleared"],"limitations":["Cookie deletion is destructive and irreversible — no undo capability","After deletion, the service cannot authenticate until new cookies are obtained via xiaohongshu-login","Deletion only clears local cookies.json file — does not invalidate the session on Xiaohongshu's servers","No confirmation or safety checks — tool will delete cookies immediately upon invocation"],"requires":["Write access to cookies.json file","No active browser sessions using the cookies (to avoid race conditions)"],"input_types":["none (no parameters required)"],"output_types":["confirmation message indicating cookies were deleted successfully"],"categories":["automation-workflow","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-xpzouying--xiaohongshu-mcp__cap_9","uri":"capability://tool.use.integration.dual.interface.dispatch.mcp.rest.api.with.shared.service.layer","name":"dual interface dispatch (mcp + rest api) with shared service layer","description":"Implements a dual-interface architecture where both MCP (/mcp endpoint) and REST API (/api/v1/... endpoints) dispatch to the same underlying XiaohongshuService methods. The service layer (service.go) contains all business logic, while mcp_handlers.go and handlers_api.go translate protocol-specific requests into service method calls. This design eliminates code duplication and ensures feature parity between interfaces.","intents":["Support both MCP clients (Claude, Cursor) and direct HTTP consumers (curl, REST clients) without maintaining separate code paths","Enable testing and debugging via REST API while supporting production MCP clients","Reduce maintenance burden by centralizing business logic in a single service layer"],"best_for":["Teams building MCP servers that need to support both MCP and REST clients","Development teams that want to test service logic via REST before deploying MCP clients","Operators who need to debug or manually invoke service methods via curl or REST clients"],"limitations":["Dual interface adds complexity to the codebase — handlers must translate between protocol-specific and service-level representations","REST API and MCP may have different latency characteristics — REST may be faster for simple queries due to lower protocol overhead","Error handling must be consistent across both interfaces — inconsistencies may confuse clients","Both interfaces share the same port (18060) — no ability to restrict MCP to a separate port for security"],"requires":["HTTP server (Gin framework) for both MCP and REST endpoints","MCP protocol implementation for /mcp endpoint","Service layer (service.go) with all business logic"],"input_types":["MCP tool call requests (JSON over HTTP) or REST API requests (JSON over HTTP)"],"output_types":["MCP tool result responses (JSON) or REST API responses (JSON)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":48,"verified":false,"data_access_risk":"high","permissions":["MCP-compatible client (Claude, Cursor, Gemini CLI, Cline, or VSCode with MCP extension)","xiaohongshu-mcp service running on port 18060","Valid Xiaohongshu session cookies (from prior xiaohongshu-login execution)","Go 1.18+ (for building xiaohongshu-login binary)","Headless Chrome or Chromium installed on the system","go-rod/rod library (included in go.mod)","Interactive terminal access for initial QR code scan","Sufficient memory to keep browser instance running (typically 100-500MB per browser)","go-rod/rod library for DOM access","Headless Chrome with JavaScript execution enabled"],"failure_modes":["MCP protocol adds ~50-100ms overhead per tool call due to JSON serialization and HTTP round-trip","Tool discovery and schema validation happens on every client connection — no caching of tool definitions","Streaming responses for large result sets (e.g., feed retrieval) may buffer in memory before transmission","QR code authentication requires interactive terminal access during initial setup — cannot be fully automated","Session cookies may expire after 30-90 days depending on Xiaohongshu's session policy; requires periodic re-authentication","Cookies stored in plaintext JSON file (cookies.json) — no encryption at rest; file permissions must be restricted manually","Browser automation adds 2-5 second latency per operation due to Chrome startup and page load times","Browser pooling adds complexity to session management — must handle browser crashes and reconnection","Shared browser context may leak state between operations — operations may interfere with each other if not properly isolated","Browser memory usage grows over time as pages are loaded and cached — no automatic garbage collection or memory limit","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.703065808400181,"quality":0.35,"ecosystem":0.48999999999999994,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.15,"match_graph":0.23,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:22.064Z","last_scraped_at":"2026-05-03T13:56:56.344Z","last_commit":"2026-04-27T02:53:12Z"},"community":{"stars":13200,"forks":2002,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=xpzouying--xiaohongshu-mcp","compare_url":"https://unfragile.ai/compare?artifact=xpzouying--xiaohongshu-mcp"}},"signature":"3LzJIOwG6NWptsWIUOInJX0QwAkcqtSVHfZhV7vlYnZA4KBLlDdqWUNegmAkDzB7Hpm6zjlee0+aM6UNRNpJBQ==","signedAt":"2026-06-21T09:30:55.309Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/xpzouying--xiaohongshu-mcp","artifact":"https://unfragile.ai/xpzouying--xiaohongshu-mcp","verify":"https://unfragile.ai/api/v1/verify?slug=xpzouying--xiaohongshu-mcp","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}