AI agents invoke keiba_data_search to trigger actions in JVLink MCP Server. 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 allows free-form SQL queries against the horse racing database. While it may be intended for read/analysis purposes, arbitrary SQL execution could include destructive statements (DROP, DELETE, UPDATE) or data exfiltration. The sibling tool 'execute_template_query' suggests this tool is more open-ended.
From the tool's definition SQLで競馬データを自由に検索・分析できる万能ツール — 'SQLで...自由に' (freely execute SQL) indicates arbitrary SQL execution capability
Documented attack patterns abuse exactly the kind of access keiba_data_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and JVLink MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for keiba_data_search:
{
"version": "1",
"default": "deny",
"tools": {
"keiba_data_search": {
"limits": [
{
"counter": "keiba_data_search_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} keiba_data_search 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.
SQLで競馬データを自由に検索・分析できる万能ツール. It is categorised as a Execute tool in the JVLink MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the JVLink MCP Server MCP server in PolicyLayer and add a rule for keiba_data_search: 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 JVLink MCP Server. Nothing to install.
keiba_data_search 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 keiba_data_search 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 keiba_data_search. 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.
keiba_data_search is provided by the JVLink MCP Server MCP server (miyamamoto/jvlink-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from JVLink MCP Server, 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.
25 JVLink MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.