set_security_mode

THE RISK

High Risk

Why set_security_mode needs a policy

This tool changes the security enforcement mode of the entire MCP server. Switching from read_only or restricted to full_access removes runtime protections and unlocks destructive/write capabilities across all connected databases (MySQL, Redis, MongoDB).

From the tool's definition 设置安全模式：read_only（只读模式）、restricted（限制模式）、full_access（完全开发模式）

Documented attack patterns abuse exactly the kind of access set_security_mode gives an agent:

POLICY

How to control set_security_mode

PolicyLayer is an MCP gateway — it sits between your AI agents and Db, and nothing reaches the server without passing your rules. This is the rule we recommend for set_security_mode:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "set_security_mode": {
      "limits": [
        {
          "counter": "set_security_mode_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

set_security_mode stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Db — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Db tools

Destructive mongodb_delete_one 删除 MongoDB 集合中的单个文档 Destructive mysql_delete 执行 MySQL DELETE 删除操作。若服务启动时已预配置 MySQL，会直接使用默认连接。 Destructive redis_del 删除 Redis 键 Execute mysql_query 执行 MySQL SQL 语句（支持 SELECT、INSERT、UPDATE、DELETE 等所有 SQL 操作）。如果服务启动时已预配置 MySQL，本工具会直接复用默认连接， Write mongodb_connect 连接到 MongoDB 数据库 Write mongodb_insert_many 向 MongoDB 集合插入多个文档 Write mongodb_insert_one 向 MongoDB 集合插入单个文档 Write mongodb_update_one 更新 MongoDB 集合中的单个文档

All 34 Db tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Db → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about set_security_mode

What does the set_security_mode tool do? +

设置安全模式：read_only（只读模式）、restricted（限制模式）、full_access（完全开发模式）. It is categorised as a Execute tool in the Db MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on set_security_mode? +

Register the Db MCP server in PolicyLayer and add a rule for set_security_mode: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Db. Nothing to install.

What risk level is set_security_mode? +

set_security_mode is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit set_security_mode? +

Yes. Add a rate_limit block to the set_security_mode rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block set_security_mode completely? +

Set action: deny in the PolicyLayer policy for set_security_mode. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides set_security_mode? +

set_security_mode is provided by the Db MCP server (wannanbigpig/db-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Db tool call.

Start from Db, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →