Send a multi-turn chat completion through Clevername's AI routing layer. Accepts full conversation history (OpenAI message format). Automatically selects the best model (Claude, GPT, Gemini, Ollama) based on privacy settings, cost, and task complexity. Injects user's connected MCP tools into the ...
Accepts raw HTML/template content (messages[].content); Single-target operation
Part of the Clevername MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents use chat_complete to create or modify resources in Clevername. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call chat_complete repeatedly, creating or modifying resources faster than any human could review. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Clevername.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
tools:
chat_complete:
rules:
- action: allow
rate_limit:
max: 30
window: 60See the full Clevername policy for all 67 tools.
Agents calling write-class tools like chat_complete have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Write risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
Send a multi-turn chat completion through Clevername's AI routing layer. Accepts full conversation history (OpenAI message format). Automatically selects the best model (Claude, GPT, Gemini, Ollama) based on privacy settings, cost, and task complexity. Injects user's connected MCP tools into the context. Use model="auto" for smart routing. Prefer this over ask_claude/ask_gpt when you need conversation history or routing flexibility. Use ask_claude/ask_gpt/ask_gemini for simple single-shot queries to a specific provider.. It is categorised as a Write tool in the Clevername MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Add a rule in your Intercept YAML policy under the tools section for chat_complete. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Clevername MCP server.
chat_complete is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the chat_complete rule in your Intercept 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 Intercept policy for chat_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.
chat_complete is provided by the Clevername MCP server (@clevername/clevername-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept