Full-text search across 64,000+ NZX market announcements (2017-present), including 62,500+ with extracted PDF text. Searches announcement titles AND full document content. Use for finding mentions of specific topics, companies, people, or events across all NZX filings. Results include: ai_categor...
AI agents call search_announcements to retrieve information from NZXplorer MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
q | string | — | Search query — searches both titles and full PDF document text |
to | string | — | End date (YYYY-MM-DD) |
from | string | — | Start date (YYYY-MM-DD) |
type | string | — | Announcement type: FLLYR, HALFYR, SHINTR, MEETING, GENERAL, SECISSUE, DVDEND, etc. |
limit | number | — | Max results (default 20) |
ticker | string | — | Filter by company ticker |
Parameters from the server's own tool schema.
This tool retrieves and queries historical NZX market announcement data without any ability to create, modify, delete, or execute operations. It is purely informational—enabling natural language queries to retrieve structured and categorized financial disclosures. The search functionality, classification metadata, and sentiment analysis are all read-only operations with no side effects on the underlying data.
From the tool's definition Tool performs 'Full-text search' across announcements and 'Searches announcement titles AND full document content.' Returns extracted data including categories, confidence scores, and topics with no modification capability described.
Attacks that exploit this kind of access
Full-text search across 64,000+ NZX market announcements (2017-present), including 62,500+ with extracted PDF text. Searches announcement titles AND full document content. Use for finding mentions of specific topics, companies, people, or events across all NZX filings. Results include: ai_category (25-category AI classification like M&A, Dividend, Regulatory, Capital Raise, Guidance, Earnings Results), ai_category_confidence (0.0-1.0), ai_sub_topics (1-3 topic tags). May also include: ai_sentiment (positive/negative/neutral/mixed), ai_sentiment_score (-1.0 to 1.0), ai_topics (array of topic labels), ai_risk_flags (array of risk indicators like profit_warning, dividend_cut), and ai_summary (concise summary). It is categorised as a Read tool in the NZXplorer MCP Server MCP Server, which means it retrieves data without modifying state.
search_announcements accepts 6 parameters: q, to, from, type, limit, ticker. The full parameter table on this page comes from the server's own tool schema.
Register the NZXplorer MCP Server MCP server in PolicyLayer and add a rule for search_announcements: 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 NZXplorer MCP Server. Nothing to install.
search_announcements 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 search_announcements 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 search_announcements. 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.
search_announcements is provided by the NZXplorer MCP Server MCP server (mambaventures/nzxplorer-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →