Route a prompt through the Adaptive LLM Gateway. Auto-selects model + provider based on task_type and routing rules.
AI agents invoke gateway.complete to trigger actions in Adaptive LLM Gateway. 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.
This tool sends prompts to external LLM providers via a gateway, triggering external API calls whose effects depend on the prompt and routing logic. It is not a simple read — it executes inference requests against potentially multiple external services. The server description mentions 'cost-aware routing' and 'multiple subscription CLIs', meaning misuse could trigger costly external API calls at scale.
From the tool's definition Route a prompt through the Adaptive LLM Gateway. Auto-selects model + provider based on task_type and routing rules.
Attacks that exploit this kind of access
Route a prompt through the Adaptive LLM Gateway. Auto-selects model + provider based on task_type and routing rules. It is categorised as a Execute tool in the Adaptive LLM Gateway MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Adaptive LLM Gateway MCP server in PolicyLayer and add a rule for gateway.complete: 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 Adaptive LLM Gateway. Nothing to install.
gateway.complete 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 gateway.complete 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 gateway.complete. 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.
gateway.complete is provided by the Adaptive LLM Gateway MCP server (renefichtmueller/adaptive-llm-gateway). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →