Step 1 of 3: Discover what actions can be automated on a website domain. Returns capabilities (search, login, add to cart, etc.) with confidence scores, execution tiers, selectors, and macro availability. Even if a domain has no indexed capabilities, universal patterns from similar sites may prov...
Part of the AIR SDK server.
Free to start. No card required.
AI agents call browse_capabilities to retrieve information from AIR SDK 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 browse_capabilities 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": {
"browse_capabilities": {}
}
}See the full AIR SDK policy for all 5 tools.
These attack patterns abuse exactly the kind of access browse_capabilities 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.
Step 1 of 3: Discover what actions can be automated on a website domain. Returns capabilities (search, login, add to cart, etc.) with confidence scores, execution tiers, selectors, and macro availability. Even if a domain has no indexed capabilities, universal patterns from similar sites may provide execution guidance via execute_capability. Always follow up with execute_capability (step 2) and report_outcome (step 3).. It is categorised as a Read tool in the AIR SDK MCP Server, which means it retrieves data without modifying state.
Register the AIR SDK MCP server in PolicyLayer and add a rule for browse_capabilities: 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 AIR SDK. Nothing to install.
browse_capabilities 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 browse_capabilities 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 browse_capabilities. 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.
browse_capabilities is provided by the AIR SDK MCP server (@arcede/air-sdk). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 AIR SDK 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.