AI agents invoke query_dolphindb to trigger actions in Dolphindb. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes arbitrary SQL scripts against a DolphinDB database. While named 'query', the server description explicitly mentions 'SQL script execution', which can include DDL (DROP, DELETE) and DML operations beyond simple reads. An AI agent could run destructive or data-modifying scripts.
From the tool's definition '在 DolphinDB 执行查询' (execute query in DolphinDB) combined with server description: 'enabling SQL script execution'
Documented attack patterns abuse exactly the kind of access query_dolphindb gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Dolphindb, and nothing reaches the server without passing your rules. This is the rule we recommend for query_dolphindb:
{
"version": "1",
"default": "deny",
"tools": {
"query_dolphindb": {
"limits": [
{
"counter": "query_dolphindb_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}query_dolphindb 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.
Free to start. No card required.
在 DolphinDB 执行查询. It is categorised as a Execute tool in the Dolphindb MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Dolphindb MCP server in PolicyLayer and add a rule for query_dolphindb: 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 Dolphindb. Nothing to install.
query_dolphindb is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the query_dolphindb 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 query_dolphindb. 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.
query_dolphindb is provided by the Dolphindb MCP server (tradercjz/dolphindb-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Dolphindb, 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.
4 Dolphindb tools catalogued and risk-classified — across an index of 43,000+ MCP servers.