Query Claude API with a prompt and optional system prompt
AI agents invoke query_claude to trigger actions in Claude Desktop API MCP. 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 sends arbitrary prompts (including custom system prompts) to the Claude API, constituting an external operation whose effects depend on the arguments. It bypasses Professional Plan limitations, meaning it can trigger API usage with potential cost implications and arbitrary instruction execution.
From the tool's definition 'Query Claude API with a prompt and optional system prompt' — triggers external API calls with arbitrary prompts and custom system prompts, executing requests against the Claude API
Documented attack patterns abuse exactly the kind of access query_claude gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Desktop API MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for query_claude:
{
"version": "1",
"default": "deny",
"tools": {
"query_claude": {
"limits": [
{
"counter": "query_claude_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}query_claude 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.
Query Claude API with a prompt and optional system prompt. It is categorised as a Execute tool in the Claude Desktop API MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Desktop API MCP server in PolicyLayer and add a rule for query_claude: 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 Claude Desktop API MCP. Nothing to install.
query_claude 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_claude 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_claude. 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_claude is provided by the Claude Desktop API MCP server (mlobo2012/claude_desktop_api_use_via_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Desktop API MCP, 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 Claude Desktop API MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.