Present content to a human and ask them to choose between options. Use this for subjective judgment, approval, preference, or tie-breaks. Avoid using it for deterministic checks or reversible low-stakes choices. The tool waits briefly for a result, then returns pending if the human has not respon...
Risk signalsAccepts raw HTML/template content (content) · Accepts URL/endpoint input (callback_url) · High parameter count (16 properties)
Part of the MeatSpace server.
Free to start. No card required.
AI agents call ask_human to retrieve information from MeatSpace without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though ask_human only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"ask_human": {}
}
}See the full MeatSpace policy for all 3 tools.
These attack patterns abuse exactly the kind of access ask_human gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Present content to a human and ask them to choose between options. Use this for subjective judgment, approval, preference, or tie-breaks. Avoid using it for deterministic checks or reversible low-stakes choices. The tool waits briefly for a result, then returns pending if the human has not responded yet.. It is categorised as a Read tool in the MeatSpace MCP Server, which means it retrieves data without modifying state.
Register the MeatSpace MCP server in PolicyLayer and add a rule for ask_human: 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 MeatSpace. Nothing to install.
ask_human 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 ask_human 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_human. 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_human is provided by the MeatSpace MCP server (https://meatspace.run/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 MeatSpace tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.