AI agents call redis_disconnect as a supporting operation in Db workflows.
This tool disconnects a Redis connection. It does not read, write, execute code, destroy data, or move money. Disconnecting a connection is a session management operation — reversible by reconnecting — and does not modify any data. It fits 'Other' as the closest category, though it could cause minor disruption if misused.
From the tool's definition 断开 Redis 数据库连接 (Disconnect Redis database connection)
Documented attack patterns abuse exactly the kind of access redis_disconnect gives an agent:
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 redis_disconnect:
{
"version": "1",
"default": "deny",
"tools": {
"redis_disconnect": {
"limits": [
{
"counter": "redis_disconnect_rate",
"window": "minute",
"max": 60,
"scope": "grant"
}
]
}
}
}redis_disconnect gets a rate cap, and everything else on the server is denied unless you say otherwise.
Free to start. No card required.
断开 Redis 数据库连接. It is categorised as a Other tool in the Db MCP Server, which means it performs auxiliary operations.
Register the Db MCP server in PolicyLayer and add a rule for redis_disconnect: 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.
redis_disconnect is a Other tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the redis_disconnect 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.
Set action: deny in the PolicyLayer policy for redis_disconnect. 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.
redis_disconnect 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.
Start from Db, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
34 Db tools catalogued and risk-classified — across an index of 43,000+ MCP servers.