AI agents call upstream_contracts to retrieve information from LLM CLI Gateway without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The description indicates a read-only operation that returns information (likely gateway configuration or upstream service contracts). The minimal description provides limited detail, reducing confidence, but the verb 'Return' and lack of mutation language suggests data retrieval with no side effects. This aligns with the Read category (retrieves or queries data; no side effects).
From the tool's definition Tool name 'upstream_contracts' and description 'Return the gateway' suggest retrieval of contract or configuration data without modification or execution.
Documented attack patterns abuse exactly the kind of access upstream_contracts gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and LLM CLI Gateway, and nothing reaches the server without passing your rules. This is the rule we recommend for upstream_contracts:
{
"version": "1",
"default": "deny",
"tools": {
"upstream_contracts": {}
}
}upstream_contracts 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.
Return the gateway. It is categorised as a Read tool in the LLM CLI Gateway MCP Server, which means it retrieves data without modifying state.
Register the LLM CLI Gateway MCP server in PolicyLayer and add a rule for upstream_contracts: 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 LLM CLI Gateway. Nothing to install.
upstream_contracts 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 upstream_contracts 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 upstream_contracts. 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.
upstream_contracts is provided by the LLM CLI Gateway MCP server (llm-cli-gateway). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from LLM CLI Gateway, 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.
46 LLM CLI Gateway tools catalogued and risk-classified — across an index of 43,000+ MCP servers.