// SCAN REPORT

Juejin

34 tools. 7 can modify or destroy data without limits.

7 write tools that can modify data. Rate limits recommended.

Last updated: 2 Jul 2026

7 can modify or destroy data

27 read-only

34 tools total

Community server · catalogue entry verified 02/07/2026

How to control Juejin ↓

TOOL MAP

What Juejin exposes to your agents

Read (27) Write / Execute (7) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Juejin tools

Execute · Medium optimize_performance This tool triggers external operations on the Juejin platform's infrastructure (cache management, statistics reset) whose effects depend on arguments. Execute · Medium run_performance_benchmark This tool executes a performance benchmarking operation on system components, which qualifies as Execute rather than Read because it actively runs tests and evaluates system performance. Write · Medium like_pin The tool modifies platform state by recording a user's like action on a post, which is reversible (unlike can typically undo it). Write · Medium update_recommendations This tool creates or modifies user preference data reversibly (recommendations can be updated again).

7 of Juejin's 34 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Juejin

PolicyLayer is an MCP gateway — it sits between your AI agents and Juejin, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "collect_article": {
    "limits": [
      {
        "counter": "collect_article_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_article_quality": {
    "limits": [
      {
        "counter": "analyze_article_quality_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Juejin — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON JUEJIN →

Instant setup, no code required.

FULL CATALOGUE

All 34 Juejin tools

EXECUTE 2 tools

Execute optimize_performance 执行性能优化操作，如清理缓存、重置统计等 Execute run_performance_benchmark 运行性能基准测试，评估系统各组件性能

WRITE 5 tools

Write collect_article 收藏文章（需要授权） Write follow_user 关注用户（需要授权） Write like_article 点赞文章（需要授权） Write like_pin 点赞沸点（需要授权） Write update_recommendations 更新用户推荐，基于最新的用户行为和兴趣

READ 27 tools

Read analyze_article_quality 分析文章质量，提供详细的质量评估和改进建议 Read analyze_content_quality 评估内容质量和受欢迎程度，提供详细的质量分析报告 Read analyze_pin_trends 分析沸点趋势，提供详细的数据统计和洞察 Read analyze_trends 分析当前热门趋势和话题，识别上升趋势和跨平台热点 Read analyze_user_interests 分析用户兴趣和行为模式，构建用户画像 Read check_auth_status 检查授权状态 Read compare_content 比较不同内容的表现和特征 Read generate_trend_report 生成综合趋势分析报告，包含跨平台数据和预测 Read generate_user_report 生成用户分析报告，包含兴趣分析、行为模式和成长建议 Read get_article_recommendations 获取个性化文章推荐，基于用户兴趣和内容质量 Read get_articles 获取掘金文章列表，支持分类、排序、分页等参数，包含质量评分和趋势分析 Read get_cache_stats 获取缓存系统统计信息，包括命中率、大小等指标 Read get_hot_topics 获取热门话题分析，识别当前最受关注的讨论话题 Read get_performance_stats 获取系统性能统计信息，包括响应时间、内存使用等指标 Read get_pin_recommendations 获取个性化沸点推荐，基于用户兴趣和内容质量 Read get_pins 获取掘金沸点列表，支持话题、排序等参数，包含情感分析和趋势信息 Read get_recommendations 获取个性化内容推荐，支持多种推荐算法和过滤条件 Read get_simple_recommendations 获取简化版内容推荐，基于当前热门内容和用户兴趣快速生成 Read get_simple_trends 获取简化版趋势分析，基于当前数据快速分析热门标签和话题 Read get_system_health 获取系统健康状态，包括性能指标、资源使用和建议 Read get_trending_articles 获取热门趋势文章，基于实时数据分析 Read get_trending_recommendations 获取基于当前趋势的推荐内容 Read get_user_profile 获取当前用户信息（需要授权） Read get_user_recommendations 获取用户推荐，发现相似用户或有影响力的用户 Read predict_popularity 预测内容受欢迎程度和传播潜力 Read search_articles 搜索掘金文章，支持关键词搜索和智能过滤 Read search_pins 搜索掘金沸点，支持关键词搜索和内容分析

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Juejin

How do I prevent bulk modifications through Juejin? +

The Juejin server has 5 write tools including collect_article, follow_user, like_article. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Juejin.

How many tools does the Juejin MCP server expose? +

34 tools across 3 categories: Execute, Read, Write. 27 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Juejin? +

Register the Juejin MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Juejin tool call.

Deterministic rules across all 34 Juejin tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON JUEJIN →

Instant setup, no code required.

34 Juejin tools catalogued and risk-classified — across an index of 43,000+ MCP servers.