Get the status and result of an async LLM job by job ID
AI agents call get-async-job-result to retrieve information from Cross-LLM MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves the status and result of an existing async job. It is a pure read operation that queries job information by ID without creating, modifying, deleting, or executing any operations. The severity is low because it only returns data and has no blast radius from misuse - retrieving job results cannot cause harm independent of what the original job was (which is handled separately).
From the tool's definition Tool description states 'Get the status and result of an async LLM job by job ID' - uses verb 'get' which retrieves data without modification. No side effects mentioned.
Documented attack patterns abuse exactly the kind of access get-async-job-result gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cross-LLM MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get-async-job-result:
{
"version": "1",
"default": "deny",
"tools": {
"get-async-job-result": {}
}
}get-async-job-result 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.
Get the status and result of an async LLM job by job ID. It is categorised as a Read tool in the Cross-LLM MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Cross-LLM MCP Server MCP server in PolicyLayer and add a rule for get-async-job-result: 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 Cross-LLM MCP Server. Nothing to install.
get-async-job-result 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 get-async-job-result 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 get-async-job-result. 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.
get-async-job-result is provided by the Cross-LLM MCP Server MCP server (jamesanz/cross-llm-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Cross-LLM 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.
23 Cross-LLM MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.