Pull fired events from your subscription feed. Returns the most recent alerts the evaluator has written to your persisted feed — each carries source, citation_uri (pipeworx:// when available), and the raw event payload. Filter by type (e.g. "sec_8k") and/or since (ISO timestamp). Set mark_read:tr...
AI agents call recent_alerts to retrieve information from Mcp Predicthq without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
type | string | — | Optional — filter to one subscription type. |
limit | number | — | Max events to return (1-200, default 50). |
since | string | — | Optional ISO timestamp — return events fired_at >= this time. |
mark_read | boolean | — | Flag the returned events read in the same call (default false). |
unread_only | boolean | — | Return only events where read_at is null (default false). |
Parameters from the server's own tool schema.
The tool primarily reads/retrieves alert data from a subscription feed. However, the mark_read:true parameter introduces a minor write side-effect by flagging events as read, which alters state. Since the primary function is retrieval and the side-effect is minimal and reversible in nature (just marking read status), Read is the most appropriate category.
From the tool's definition Pull fired events from your subscription feed. Returns the most recent alerts the evaluator has written to your persisted feed
Attacks that exploit this kind of access
Pull fired events from your subscription feed. Returns the most recent alerts the evaluator has written to your persisted feed — each carries source, citation_uri (pipeworx:// when available), and the raw event payload. Filter by type (e.g. "sec_8k") and/or since (ISO timestamp). Set mark_read:true to flag returned events read so the next call only shows newer ones. Polls work fine; the same feed is also at GET registry.pipeworx.io/alerts.json for scripts and dashboards. It is categorised as a Read tool in the Mcp Predicthq MCP Server, which means it retrieves data without modifying state.
recent_alerts accepts 5 parameters: type, limit, since, mark_read, unread_only. The full parameter table on this page comes from the server's own tool schema.
Register the Mcp Predicthq MCP server in PolicyLayer and add a rule for recent_alerts: 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 Mcp Predicthq. Nothing to install.
recent_alerts 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 recent_alerts 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 recent_alerts. 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.
recent_alerts is provided by the Mcp Predicthq MCP server (pipeworx-io/mcp-predicthq). 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 →