xhs-mcp (ShunL12324/xhs-mcp) is an MCP server listed on the M8ven Trust Index. It scores 50 out of 100, grade D. It declares 70 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
D
Caution
50/100

xhs-mcp

小红书 MCP 服务器，使 AI 助手能够搜索、浏览、发布和互动小红书内容，支持多账号管理与自动浏览。

→ ShunL12324/xhs-mcp· listed on glama

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

ShunL12324

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

Glamanot scored here

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
⚠️
Known vulnerabilities in dependencies: 8 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
✅
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 1 credential: GEMINI_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes35 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

xhs_list_accounts

List all registered Xiaohongshu accounts with their status and last activity.

xhs_add_account

Start login process for a new or existing account. Returns a QR code URL for scanning. After user scans the QR code, call xhs_check_login_session to check status and complete the login. Flow: 1. Call xhs_add_account -> get sessionId and qrCodeUrl 2. Show QR code URL to user for scanning 3. Call xhs…

xhs_check_login_session

Check login status and complete the login process. Call this after user scans the QR code from xhs_add_account. May return verification_required if SMS code is needed. Status values: - waiting_scan: QR code not scanned yet - scanned: QR code scanned, processing - verification_required: SMS code nee…

xhs_submit_verification

Submit SMS verification code to complete login. Only call this when xhs_check_login_session returns status: verification_required. Verification code expires in 1 minute.

xhs_remove_account

Remove a registered account and delete its session data.

xhs_set_account_config

Update account configuration such as name, proxy or status.

xhs_get_account_prompt

Get the prompt file content for an account. Prompts control AI behavior during explore (note selection and comment generation).

xhs_set_account_prompt

Update the prompt file content for an account. Use this to customize AI behavior during explore.

xhs_check_auth_status

Check if an account is currently logged in to Xiaohongshu. If logged in, syncs user profile (nickname, userId, etc.) to database.

xhs_search

Search for notes on Xiaohongshu. Supports scrolling to load more results and filtering. Returns notes with id, xsecToken, title, cover, user info, and likes.

xhs_get_note

Get details of a specific note including content, images, stats, and comments. Use xsecToken from search results for reliable access.

xhs_user_profile

Get user profile information including basic info, stats (followers, fans), and their published notes.

xhs_list_feeds

Get homepage recommended feeds.

xhs_publish_video

Publish a new video note to Xiaohongshu. Opens a visible browser window for the publishing process. Requires login.

xhs_like_feed

Like or unlike a note on Xiaohongshu. Requires login.

xhs_favorite_feed

Favorite (collect) or unfavorite a note on Xiaohongshu. Requires login.

xhs_post_comment

Post a comment on a note. Requires login.

xhs_reply_comment

Reply to a comment on a note. Requires login.

xhs_like_comment

Like or unlike a comment on Xiaohongshu. Requires login.

xhs_delete_cookies

Delete saved login cookies/session for an account. Use this to log out or re-authenticate.

xhs_get_account_stats

Get operation statistics for an account including total operations, success rate, and breakdown by action type.

xhs_get_operation_logs

Query operation logs for an account. Returns recent operations with their results.

xhs_download_images

Download all images from a note to local storage.

xhs_download_video

Download video from a note to local storage.

xhs_create_draft

Create a note draft from Markdown content and screenshots. AI will automatically generate beautiful Xiaohongshu-style images (cover, screenshot annotations, text slides).

xhs_list_drafts

List all note drafts.

xhs_get_draft

Get details of a specific draft.

xhs_update_draft

Update a draft. Can modify title, content, tags, or images.

xhs_delete_draft

Delete a draft and its associated images.

xhs_publish_draft

Publish a draft to Xiaohongshu. Supports publishing to multiple accounts with identical content.

xhs_get_my_notes

Get list of published notes from the current account's creator center. Fetches from API and caches to database. Returns notes with stats (views, likes, comments, etc.) and permission status.

xhs_query_my_notes

Query cached published notes from database. Supports multiple filter conditions. Use xhs_get_my_notes first to populate the cache.

xhs_get_notifications

Get notifications for the current account. Returns mentions (comments/replies), likes, and connections (follows). Each notification contains enough info to reply or interact.

xhs_explore

Automatically browse the Xiaohongshu explore page with human-like behavior. Uses AI to select interesting notes, then likes and comments based on probability. Features: - Scrolls like a human (2-3 wheel scrolls, then pause to read) - AI selects which notes to open based on interests - Probability-b…

xhs_stop_explore

Stop a running explore session. Use this to gracefully stop an ongoing explore session. The session will complete its current action and then stop. If no sessionId is provided, stops all active explore sessions for the account.

// known CVEs in dependencies8 high22 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

high@modelcontextprotocol/sdk@1.23.0GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.23.0GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.23.0GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

highhono@4.7.0GHSA-3vhc-576x-3qv4

Hono JWK Auth Middleware has JWT algorithm confusion when JWK lacks "alg" (untrusted header.alg fallback)

highhono@4.7.0GHSA-88fw-hqm2-52qc

hono: CORS Middleware reflects any Origin with credentials when `origin` defaults to the wildcard

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configGEMINI_ANALYSIS_MODEL
🔐 secretGEMINI_API_KEYGemini API 密钥（AI 图片生成必需）
configGEMINI_BASE_URL
configGEMINI_IMAGE_GENERATE_MODELgemini-3-pro-image 图片生成模型
configGEMINI_MODEL
configXHS_MCP_DATA_DIR~/.xhs-mcp 数据存储目录
configXHS_MCP_HEADLESStrue 是否使用无头浏览器
configXHS_MCP_KEEP_OPENfalse 操作完成后保持浏览器打开
configXHS_MCP_LOG_LEVEL
configXHS_MCP_PORT
configXHS_MCP_REQUEST_INTERVAL2000 请求间隔（毫秒）
configXHS_MCP_TIMEOUT_PAGE_LOAD
configXHS_MCP_TIMEOUT_VIDEO_UPLOAD
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

70/70 tools missing one or more hints — xhs_list_accounts (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); xhs_add_account (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); xhs_check_login_session (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +67 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tests exist

No test files found

Add tests that exercise each declared tool.

Shell command execution

10 child_process calls — runs shell commands

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Secrets not logged

12 secret values sent to console.log

Redact or omit secret values from log output.

No arbitrary install scripts

Has postinstall/preinstall script — runs arbitrary code on npm install

Remove postinstall/preinstall hooks unless they’re essential.

Production dependencies are patched

0 critical, 8 high severity in production deps — @modelcontextprotocol/sdk@1.23.0 (high), @modelcontextprotocol/sdk@1.23.0 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Domain consistency

npm scope @sillyl12324 doesn't match GitHub owner shunl12324

Use the same org name across GitHub, npm, and your homepage so users can verify the publisher.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 8 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/shunl12324/xhs-mcp?variant=verified)](https://m8ven.ai/mcp/shunl12324/xhs-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: cb963621390dfa22d19103ed88ab55a3d57a74ba
code hash: b823e38ca9bc2dd83512bd784fbd0634f3cfa619327bf8abd0acfedb7aa476f8
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client