AI agents invoke ask_claude to trigger actions in Proxima. 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.
Based on the server context, this tool sends prompts to the Claude AI provider and retrieves responses, constituting an external operation execution. Sibling tools like 'ask_chatgpt', 'ask_gemini', 'ask_perplexity' follow the same pattern. Empty description lowers confidence.
From the tool's definition Tool name 'ask_claude' on a server described as an AI gateway that triggers external AI provider operations; description is empty and uninformative.
Documented attack patterns abuse exactly the kind of access ask_claude gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Proxima, and nothing reaches the server without passing your rules. This is the rule we recommend for ask_claude:
{
"version": "1",
"default": "deny",
"tools": {
"ask_claude": {
"limits": [
{
"counter": "ask_claude_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}ask_claude 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.
ask_claude. It is categorised as a Execute tool in the Proxima MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Proxima MCP server in PolicyLayer and add a rule for ask_claude: 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 Proxima. Nothing to install.
ask_claude 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 ask_claude 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 ask_claude. 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.
ask_claude is provided by the Proxima MCP server (zen4-bit/proxima). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 50 Proxima tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
50 Proxima tools catalogued and risk-classified — across an index of 42,500+ MCP servers.