F5 Access-Layer Policy Guard. Call BEFORE automating a gated source to check whether an {action} on a {source} is permitted from a {jurisdiction}. Returns {decision: allow|warn|block, reason, category}. It BLOCKS jurisdiction-illegal funding/betting (e.g. foreign sportsbooks from Turkey), WARNS o...
AI agents call access_policy_check to retrieve information from Yaver without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
action | string | Yes | data|read|observe|scrape (always allowed) | login|signup|register | bet|place_bet|deposit|withdraw (funding/placing). |
source | string | Yes | Domain or service name, e.g. 'betfair.com', 'misli.com', 'superbet.rs'. |
jurisdiction | string | — | ISO-ish code for where the user physically is, e.g. 'TR','US','RS'. Omit if unknown (a gambling source + unknown jurisdiction returns 'warn'). |
Parameters from the server's own tool schema.
Even though access_policy_check 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.
Attacks that exploit this kind of access
F5 Access-Layer Policy Guard. Call BEFORE automating a gated source to check whether an {action} on a {source} is permitted from a {jurisdiction}. Returns {decision: allow|warn|block, reason, category}. It BLOCKS jurisdiction-illegal funding/betting (e.g. foreign sportsbooks from Turkey), WARNS on account actions (login/signup) in such jurisdictions, and ALLOWS public-data reading everywhere. Unknown sources => allow (it does not over-block legitimate automation). You MUST honor a 'block' (do not place/fund bets) and surface a 'warn' to the user. This is the boundary that keeps remote-hands legitimate. It is categorised as a Read tool in the Yaver MCP Server, which means it retrieves data without modifying state.
access_policy_check accepts 3 parameters: action, source, jurisdiction. Required: action, source. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for access_policy_check: 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 Yaver. Nothing to install.
access_policy_check 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 access_policy_check 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 access_policy_check. 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.
access_policy_check is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.