// SCAN REPORT

ThinkMem

28 tools. 19 can modify or destroy data without limits.

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

Last updated: 12 Jun 2026

19 can modify or destroy data

9 read-only

28 tools total

Community server · catalogue entry verified 12/06/2026

How to control ThinkMem ↓

TOOL MAP

What ThinkMem exposes to your agents

Read (9) Write / Execute (14) Destructive / Financial (5)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous ThinkMem tools

Destructive · High clearList This tool permanently and irreversibly deletes all data stored in a ListMemory structure. Destructive · High deleteListElement This tool irreversibly removes data from a memory structure. Destructive · High deleteListElementByName This tool deletes data from memory structures without reversibility. Destructive · High deleteMemory This tool permanently deletes entire memory blocks and their contents without possibility of reversal.

19 of ThinkMem's 28 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control ThinkMem

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

Deny destructive operations

{
  "clearList": {
    "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

{
  "appendListElement": {
    "limits": [
      {
        "counter": "appendlistelement_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "getListElement": {
    "limits": [
      {
        "counter": "getlistelement_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 ThinkMem — 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 THINKMEM →

Free to start. No card required.

FULL CATALOGUE

All 28 ThinkMem tools

DESTRUCTIVE 5 tools

Destructive clearList 清空ListMemory中的所有元素，此操作不可逆。 Destructive deleteListElement 删除ListMemory中指定位置的元素，后续元素会自动前移。 Destructive deleteListElementByName 根据元素名称删除ListMemory中的指定元素，利用名称唯一性机制定位。 Destructive deleteMemory 删除指定的Memory存储块及其包含的所有数据。 Destructive deleteRawLines 删除RawMemory中指定行范围的文本内容，后续行会自动前移。

WRITE 14 tools

Write appendListElement 在ListMemory的末尾添加新元素。适用于所有角色模式的ListMemory，但仅建议在array模式下使用。 Write addGraphMemory 创建一个新的GraphMemory存储块，用于表示图结构数据。支持tree（树结构）和graph（图结构）两种模式，适用于知识图谱、关系网络等场景。 Write addListMemory 创建一个新的ListMemory存储块，作为有序集合使用。支持array（数组）、deque（双端队列）、stack（栈）三种角色模式。 Write addRawMemory 创建一个新的RawMemory存储块，用于存储无结构的原始文本数据。支持后续的文本编辑、摘要管理和智能搜索功能。 Write desummarizeRawLines 删除RawMemory指定行范围的摘要，不影响原始文本内容。 Write insertListElement 在ListMemory的指定位置插入新元素，用于精确控制元素顺序。 Write insertRawLines 在RawMemory指定行位置插入新文本内容，原位置行及后续行会自动后移。 Write popDequeElement 从双端队列模式ListMemory的前端或后端弹出元素，遵循先进先出或后进先出原则。 Write popStackElement 从栈模式ListMemory的顶部弹出元素，遵循后进先出原则。 Write pushDequeElement 在双端队列模式ListMemory的前端或后端添加元素。 Write pushStackElement 在栈模式ListMemory的顶部添加新元素，遵循后进先出原则。 Write replaceRawLines 替换RawMemory中指定行范围的文本内容，支持模式匹配定位。 Write summarizeRawLines 为RawMemory的指定行范围添加摘要文本。摘要用于对大段文本进行概括性描述，便于快速理解和检索。粒度可以较细。此过程应该由工具调用方自觉主动完成。 Write writeRaw 向RawMemory写入文本内容，支持覆盖模式或追加模式。

READ 9 tools

Read getListElement 获取ListMemory中指定位置的元素内容，仅用于查询操作。 Read readRawLines 读取RawMemory的文本内容，支持原始数据读取和智能摘要模式。 Read searchListElements 搜索ListMemory中名称中包含指定模式的元素。返回匹配的元素索引和内容，默认支持不区分大小写正则表达式。可空以获取全部。 Read searchMemory 搜索和筛选Memory存储块，支持按名称模式匹配和按类型过滤。返回符合条件的Memory列表。默认支持不区分大小写正则表达式。可空以获取全部。 Read searchRawLines 在RawMemory中搜索包含指定模式的文本行。返回匹配的行号和行内容，默认支持不区分大小写正则表达式。可空以获取全部。 Read serverStatus 检查服务器运行状态和统计信息 Read peekDequeElement 查看双端队列模式ListMemory的前端或后端元素，用于预览队列状态。 Read peekStackElement 查看栈模式ListMemory的顶部元素，用于预览栈顶状态。 Read ThinkMemAIGuide 获取完整的THINK-MEM AI助手操作指南，包含NamePath定位系统详解、实际应用范例和最佳实践。帮助AI助手快速掌握如何使用ThinkMem系统进行记忆管理和智能交互。当AI助手使用ThinkMem前务必阅读完

EXPLORE

Related servers

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

FAQ

Questions about ThinkMem

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

Yes. The ThinkMem server exposes 5 destructive tools including clearList, deleteListElement, deleteListElementByName. 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 ThinkMem? +

The ThinkMem server has 14 write tools including appendListElement, addGraphMemory, addListMemory. 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 ThinkMem.

How many tools does the ThinkMem MCP server expose? +

28 tools across 3 categories: Destructive, Read, Write. 9 are read-only. 19 can modify, create, or delete data.

How do I enforce a policy on ThinkMem? +

Register the ThinkMem 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 ThinkMem tool call.

Deterministic rules across all 28 ThinkMem tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON THINKMEM →

Free to start. No card required.

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