Premium reliability breakdown. For every monitored feed, a 0-100 composite reliability score with subscores (uptime, availability, staleness rate, dark rate), a sample-size trust tier, and a low_coverage flag, scored from rolling ok/stale/dark counts probed every 5 minutes. Ranked, with low-sampl...
Risk signalsBulk/mass operation — affects multiple targets
Part of the Terminalfeed server.
Free to start. No card required.
AI agents call tf_premium_feed_reliability to retrieve information from Terminalfeed 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 tf_premium_feed_reliability 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": {
"tf_premium_feed_reliability": {}
}
}See the full Terminalfeed policy for all 35 tools.
These attack patterns abuse exactly the kind of access tf_premium_feed_reliability 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.
Premium reliability breakdown. For every monitored feed, a 0-100 composite reliability score with subscores (uptime, availability, staleness rate, dark rate), a sample-size trust tier, and a low_coverage flag, scored from rolling ok/stale/dark counts probed every 5 minutes. Ranked, with low-sample feeds parked separately. captured_at is the monitor real check time, so a stalled monitor (>48h) no-charges. The free preview is GET /api/feed-reliability (top-line table, no auth); this paid tier adds the signed receipt and the full per-feed breakdown. Costs 2 credits ($0.04 USDC). Requires Authorization: Bearer tf_live_<64-char-hex>.. It is categorised as a Read tool in the Terminalfeed MCP Server, which means it retrieves data without modifying state.
Register the Terminalfeed MCP server in PolicyLayer and add a rule for tf_premium_feed_reliability: 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 Terminalfeed. Nothing to install.
tf_premium_feed_reliability 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 tf_premium_feed_reliability 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 tf_premium_feed_reliability. 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.
tf_premium_feed_reliability is provided by the Terminalfeed MCP server (https://terminalfeed.io/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 35 Terminalfeed 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.