// SCAN REPORT

Zhiyi

3 tools. 2 can modify or destroy data without limits.

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

Last updated: 7 Jul 2026

2 can modify or destroy data

1 read-only

3 tools total

Community server · catalogue entry checked 07/07/2026 · full schemas captured for 3 of 3 tools

How to control Zhiyi ↓

TOOL MAP

What Zhiyi exposes to your agents

Read (1) Write / Execute (2) Destructive / Financial (0)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Zhiyi costs in tokens

985 tokens of tool definitions, loaded on every request

0.5% of a 200k context window

749 heaviest tool: memory_remember

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Zhiyi tools

Write · Low memory_feedback This tool submits feedback on memory recall results, which is a write operation (creating/modifying feedback data). Write · Medium memory_remember The tool writes/creates a new memory capture draft based on agent experience.

2 of Zhiyi's 3 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Zhiyi

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

Rate limit write operations

{
  "memory_feedback": {
    "limits": [
      {
        "counter": "memory_feedback_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "memory_recall": {
    "limits": [
      {
        "counter": "memory_recall_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 Zhiyi — 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 ZHIYI →

Instant setup, no code required.

FULL CATALOGUE

All 3 Zhiyi tools

WRITE 2 tools

Write memory_feedback 对 Recall 结果提交效果反馈 Write memory_remember Agent 完成任务后提交经验 Event，生成 Capture 草稿供人工确认发布。payload 各字段对应 Fact Block，必须分别填写、内容不得重复：observation=观察到的现象/问题；decisi

READ 1 tools

Read memory_recall 根据任务上下文召回相关经验 Fact Blocks

FAQ

Questions about Zhiyi

How do I prevent bulk modifications through Zhiyi? +

The Zhiyi server has 2 write tools including memory_feedback, memory_remember. 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 Zhiyi.

How many tools does the Zhiyi MCP server expose? +

3 tools across 1 categories: Read. 1 are read-only. 2 can modify, create, or delete data.

How do I enforce a policy on Zhiyi? +

Register the Zhiyi 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 Zhiyi tool call.

Deterministic rules across all 3 Zhiyi tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ZHIYI →

Instant setup, no code required.

3 Zhiyi tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Zhiyi's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →