Search The Agent Times agent-news layer across structured events, articles, and agent-action/product metadata. Uses backend typo correction, alias expansion, required-term coverage, global ranking, and low-confidence rejection. Returns search_confidence, warnings, relevance_score, match_quality, ...
AI agents call tat_search to retrieve information from The Agent Times without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
tag | string | — | Optional tag filter |
sort | string | — | Article sort order |
limit | integer | — | Number of results (max 20, default 10) |
query | string | — | Short entity-rich English search query for agent-news, articles, products, actions, or events |
topic | string | — | Optional topic filter |
intent | string | — | Optional intent filter |
section | string | — | Optional article section filter |
urgency | string | — | Optional event urgency filter |
actionability | string | — | Optional actionability filter |
include_events | boolean | — | Include agent event matches (default true) |
include_articles | boolean | — | Include article matches (default true) |
include_products | boolean | — | Include agent-action/product metadata matches (default true) |
Parameters from the server's own tool schema.
Even though tat_search 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.
Risk signalsAccepts freeform code/query input (query) · High parameter count (12 properties)
Documented attack patterns abuse exactly the kind of access tat_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and The Agent Times, and nothing reaches the server without passing your rules. This is the rule we recommend for tat_search:
{
"version": "1",
"default": "deny",
"tools": {
"tat_search": {}
}
} tat_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search The Agent Times agent-news layer across structured events, articles, and agent-action/product metadata. Uses backend typo correction, alias expansion, required-term coverage, global ranking, and low-confidence rejection. Returns search_confidence, warnings, relevance_score, match_quality, matched_terms, missing_terms, sources, confidence, Ethics Engine score, agent voice score, and standard receipt. It is categorised as a Read tool in the The Agent Times MCP Server, which means it retrieves data without modifying state.
tat_search accepts 12 parameters: tag, sort, limit, query, topic, intent, section, urgency, actionability, include_events, include_articles, include_products. The full parameter table on this page comes from the server's own tool schema.
Register the The Agent Times MCP server in PolicyLayer and add a rule for tat_search: 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 The Agent Times. Nothing to install.
tat_search 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 tat_search 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 tat_search. 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.
tat_search is provided by the The Agent Times MCP server (theagenttimes/news). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 22 The Agent Times tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
22 The Agent Times tools catalogued and risk-classified — across an index of 42,500+ MCP servers.