Cn Funds

24 tools. 4 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated:

4 can modify or destroy data
20 read-only
24 tools total

Community server · catalogue entry verified 29/06/2026

How to control Cn Funds ↓

What Cn Funds exposes to your agents

Read (20) Write / Execute (2) Destructive / Financial (2)
Critical Risk

The most dangerous Cn Funds tools

4 of Cn Funds's 24 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Cn Funds

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

Deny destructive operations
{
  "remove_portfolio": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "save_portfolio": {
    "limits": [
      {
        "counter": "save_portfolio_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "check_reminders": {
    "limits": [
      {
        "counter": "check_reminders_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register Cn Funds — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON CN FUNDS →

Instant setup, no code required.

All 24 Cn Funds tools

READ 20 tools
Read check_reminders 检查是否有到期的提醒(AI 应在每次对话开始时主动调用此工具)。返回当前到期未触发的提醒列表,同一提醒每天只触发一次。 Read get_fund_accumulated_performance 获取基金累计收益走势,并与沪深300及同类平均对比 Read get_fund_batch_info 批量获取多只基金的基本信息(净值、涨跌幅) Read get_fund_estimate 获取基金实时估值数据(盘中估算净值和涨跌幅) Read get_fund_info 获取基金详细信息(类型、公司、经理、规模、近期收益排名等) Read get_fund_manager_detail 获取基金现任经理详细信息(简历、照片、管理年限) Read get_fund_manager_list 获取基金历任经理列表(任职起止日期、任职天数、任职期间涨幅) Read get_fund_net_value_history 获取基金历史净值走势(单位净值、累计净值) Read get_fund_position 获取基金股票持仓明细(持仓股票、占比、较上期变化) Read get_fund_valuation_detail 获取基金当日估值走势(日内分时估值变化数据) Read get_market_capital_flow 获取A股大盘当日资金流向(主力/超大单/大单/中单/小单净流入,单位亿元) Read get_market_overview 获取A股大盘概况(上证指数、深证成指的价格/涨跌/成交额/涨跌家数) Read get_northbound_capital 获取沪深港通(北向/南向)资金实时流向数据(沪股通/深股通/港股通净流入,单位亿元) Read get_portfolio 查看我当前保存的所有基金持仓列表 Read get_portfolio_profit 一键查询我所有持仓的今日收益和总收益(基于实时估值计算) Read get_reminders 查看当前所有定时提醒设置 Read get_sector_capital_flow 获取板块资金流向排行(行业板块或概念板块的资金净流入排名) Read get_stock_quote 获取股票或指数的实时行情报价(价格、涨跌幅、成交额) Read get_stock_trend 获取股票或指数的日内分时走势数据 Read search_fund 根据关键词搜索基金(支持基金名称、代码、拼音缩写)

Related servers

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

Questions about Cn Funds

Can an AI agent delete data through the Cn Funds MCP server? +

Yes. The Cn Funds server exposes 2 destructive tools including remove_portfolio, remove_reminder. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Cn Funds? +

The Cn Funds server has 2 write tools including save_portfolio, set_reminder. 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 Cn Funds.

How many tools does the Cn Funds MCP server expose? +

24 tools across 3 categories: Destructive, Read, Write. 20 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on Cn Funds? +

Register the Cn Funds 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 Cn Funds tool call.

Deterministic rules across all 24 Cn Funds tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

24 Cn Funds tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.