AI agents invoke call-chatgpt to trigger actions in Cross-LLM 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 executes requests against an external LLM API (OpenAI/ChatGPT). The effects depend entirely on the prompt arguments passed, which could include generating harmful content, exfiltrating data via prompt injection, or chaining with other tools. It is an external operation trigger, placing it in the Execute category.
From the tool's definition "Call OpenAI" — triggers an external API call to OpenAI's ChatGPT service with user-supplied prompts
Documented attack patterns abuse exactly the kind of access call-chatgpt 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 call-chatgpt:
{
"version": "1",
"default": "deny",
"tools": {
"call-chatgpt": {
"limits": [
{
"counter": "call-chatgpt_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}call-chatgpt 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.
Call OpenAI. It is categorised as a Execute tool in the Cross-LLM MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cross-LLM MCP Server MCP server in PolicyLayer and add a rule for call-chatgpt: 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.
call-chatgpt 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 call-chatgpt 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 call-chatgpt. 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.
call-chatgpt 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.