Search for values in a JSON file. Use when you do not know the path to a value in a large JSON file, but have some idea what the value is.
AI agents call json_query_search_values to retrieve information from JSON Query MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs value lookup and extraction within JSON data structures. It retrieves information based on search criteria but does not create, modify, delete, or execute any operations. The tool has no side effects and is purely informational in nature.
From the tool's definition Tool description states 'Search for values in a JSON file' with the purpose of enabling LLMs to 'search and extract information from large JSON data.' The verb 'search' and the read-only nature of querying JSON files without modification indicate retrieval…
Documented attack patterns abuse exactly the kind of access json_query_search_values gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and JSON Query MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for json_query_search_values:
{
"version": "1",
"default": "deny",
"tools": {
"json_query_search_values": {}
}
}json_query_search_values is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search for values in a JSON file. Use when you do not know the path to a value in a large JSON file, but have some idea what the value is. It is categorised as a Read tool in the JSON Query MCP MCP Server, which means it retrieves data without modifying state.
Register the JSON Query MCP server in PolicyLayer and add a rule for json_query_search_values: 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 JSON Query MCP. Nothing to install.
json_query_search_values is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the json_query_search_values 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 json_query_search_values. 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.
json_query_search_values is provided by the JSON Query MCP server (mgraczyk/json-query-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from JSON Query 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.
3 JSON Query MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.