Execute an Artifactory Query Language (AQL) query to search for artifacts, builds, or other entities in JFrog Artifactory. AQL is a powerful query language for searching and filtering artifacts in Artifactory repositories. It supports complex criteria, sorting, pagination, and more.
AI agents invoke jfrog_execute_aql_query to trigger actions in JFrog 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.
Although AQL queries are typically read-only by design, the tool is classified as Execute rather than Read because: (1) the description explicitly uses 'Execute' as the action verb, (2) AQL is a query language that can perform complex operations with side effects depending on implementation (aggregations, transformations), and (3) as an 'Experimental' MCP server with access to JFrog Platform APIs, the actual…
From the tool's definition The tool description states it 'Execute[s] an Artifactory Query Language (AQL) query' and supports 'complex criteria, sorting, pagination, and more.' The verb 'Execute' combined with a query language (AQL) that can perform complex operations on a central…
Documented attack patterns abuse exactly the kind of access jfrog_execute_aql_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and JFrog MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for jfrog_execute_aql_query:
{
"version": "1",
"default": "deny",
"tools": {
"jfrog_execute_aql_query": {
"limits": [
{
"counter": "jfrog_execute_aql_query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}jfrog_execute_aql_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.
Execute an Artifactory Query Language (AQL) query to search for artifacts, builds, or other entities in JFrog Artifactory. AQL is a powerful query language for searching and filtering artifacts in Artifactory repositories. It supports complex criteria, sorting, pagination, and more. It is categorised as a Execute tool in the JFrog MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the JFrog MCP Server MCP server in PolicyLayer and add a rule for jfrog_execute_aql_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 JFrog MCP Server. Nothing to install.
jfrog_execute_aql_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 jfrog_execute_aql_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 jfrog_execute_aql_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.
jfrog_execute_aql_query is provided by the JFrog MCP Server MCP server (jfrog/mcp-jfrog). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from JFrog 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.
36 JFrog MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.