Push a user's contact info to a business so they can call/email/text back. Use this when a question can't be answered without human contact (custom quote, after-hours scheduling, complaint, complex combo). Idempotent on idempotency_key within a 24h window — agent retries don't spam the business. ...
Risk signalsHigh parameter count (10 properties)
Part of the AdvocateMCP server.
Free to start. No card required.
AI agents call request_callback to retrieve information from AdvocateMCP 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 request_callback 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": {
"request_callback": {}
}
}See the full AdvocateMCP policy for all 10 tools.
These attack patterns abuse exactly the kind of access request_callback 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.
Push a user's contact info to a business so they can call/email/text back. Use this when a question can't be answered without human contact (custom quote, after-hours scheduling, complaint, complex combo). Idempotent on idempotency_key within a 24h window — agent retries don't spam the business. Returns delivery status the agent can quote to the user.. It is categorised as a Read tool in the AdvocateMCP MCP Server, which means it retrieves data without modifying state.
Register the Advocate MCP server in PolicyLayer and add a rule for request_callback: 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 AdvocateMCP. Nothing to install.
request_callback 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 request_callback 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 request_callback. 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.
request_callback is provided by the Advocate MCP server (https://api.advocatemcp.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 10 AdvocateMCP 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.