Send a chat message to the vLLM server. Supports multi-turn conversations.
AI agents invoke vllm_chat to trigger actions in vLLM 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.
This tool sends requests to an external vLLM inference server and triggers model execution. It is not a simple read/query of stored data — it causes the server to run inference (i.e., execute a language model) and produce outputs. The blast radius is medium: misuse could generate harmful content, consume significant compute resources, or be used to probe model behavior, but it does not directly modify or delete data.
From the tool's definition Send a chat message to the vLLM server. Supports multi-turn conversations.
Documented attack patterns abuse exactly the kind of access vllm_chat gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and vLLM MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for vllm_chat:
{
"version": "1",
"default": "deny",
"tools": {
"vllm_chat": {
"limits": [
{
"counter": "vllm_chat_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}vllm_chat 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.
Send a chat message to the vLLM server. Supports multi-turn conversations. It is categorised as a Execute tool in the vLLM MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the vLLM MCP Server MCP server in PolicyLayer and add a rule for vllm_chat: 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 vLLM MCP Server. Nothing to install.
vllm_chat 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 vllm_chat 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 vllm_chat. 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.
vllm_chat is provided by the vLLM MCP Server MCP server (micytao/vllm-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from vLLM 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.
12 vLLM MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.