OpenAI-compatible chat completions across every frontier model on one endpoint — GPT-5, Claude, Gemini, Grok, DeepSeek, Llama, Mistral and ~290 more. POST { model, messages, max_tokens?, temperature?, top_p?, stop? } and get back a standard chat.completion (choices[].message + usage). Pay per cal...
AI agents call ai.chat to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though ai.chat only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
OpenAI-compatible chat completions across every frontier model on one endpoint — GPT-5, Claude, Gemini, Grok, DeepSeek, Llama, Mistral and ~290 more. POST { model, messages, max_tokens?, temperature?, top_p?, stop? } and get back a standard chat.completion (choices[].message + usage). Pay per call in USDC via x402 — no accounts, no provider keys, no subscriptions. Price scales with the model and max_tokens and is quoted in the 402. List selectable models at GET /api/ai/models. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for ai.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 Mcp. Nothing to install.
ai.chat 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 ai.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 ai.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.
ai.chat is provided by the MCP server (@2sio/mcp). 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 →