The "always start here" premium call for autonomous agents. Composes 13 upstream sources into a curated world-state snapshot: BTC ticker, Fear and Greed, VIX, Fed funds rate, USD-base forex (EUR/JPY/GBP/CHF), HN front page top 5, significant earthquakes 24h, upcoming space launches, top Polymarke...
Part of the Terminalfeed server.
Free to start. No card required.
AI agents invoke tf_premium_agent_context to trigger processes or run actions in Terminalfeed. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
tf_premium_agent_context can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"tf_premium_agent_context": {
"limits": [
{
"counter": "tf_premium_agent_context_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full Terminalfeed policy for all 35 tools.
These attack patterns abuse exactly the kind of access tf_premium_agent_context gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
The "always start here" premium call for autonomous agents. Composes 13 upstream sources into a curated world-state snapshot: BTC ticker, Fear and Greed, VIX, Fed funds rate, USD-base forex (EUR/JPY/GBP/CHF), HN front page top 5, significant earthquakes 24h, upcoming space launches, top Polymarket markets, and infrastructure status (GitHub, Cloudflare, OpenAI, Anthropic). Returns BOTH a structured JSON context object for parsers AND a pre-formatted system_prompt string (~350 tokens) the agent pastes verbatim into its LLM context. Saves the agent from making 13 separate calls and writing a formatter. Curation choice (which signals matter, how to compress them) is the moat. Costs 2 credits ($0.04 USDC). 5-min cache. Bearer auth required.. It is categorised as a Execute tool in the Terminalfeed MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Terminalfeed MCP server in PolicyLayer and add a rule for tf_premium_agent_context: 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_agent_context is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the tf_premium_agent_context 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_agent_context. 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_agent_context 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.