AI agents invoke your_own_query to trigger actions in Claude Code. 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.
The tool accepts arbitrary user-defined queries in the context of a server that runs code, edits files, and simulates commands. 'Custom query' implies open-ended execution potential. Since it sits alongside code-modifying and command-execution tools, misuse could trigger code execution or file modification.
From the tool's definition 'Sends a custom query with context' — arbitrary/custom query with unspecified scope; server description lists it alongside code execution tools like simulate_command, edit_code, fix_code
Documented attack patterns abuse exactly the kind of access your_own_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Code, and nothing reaches the server without passing your rules. This is the rule we recommend for your_own_query:
{
"version": "1",
"default": "deny",
"tools": {
"your_own_query": {
"limits": [
{
"counter": "your_own_query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}your_own_query 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.
Sends a custom query with context. It is categorised as a Execute tool in the Claude Code MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Code MCP server in PolicyLayer and add a rule for your_own_query: 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 Code. Nothing to install.
your_own_query 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 your_own_query 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 your_own_query. 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.
your_own_query is provided by the Claude Code MCP server (kunihiros/claude-code-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Code, 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.
7 Claude Code tools catalogued and risk-classified — across an index of 43,000+ MCP servers.