Build a Daily Situation-Briefing Agent with MCP Prompts and Area Watch

Most people wire an AI agent to live data and then ask it one-off questions. The higher-value pattern is a routine: the same briefing, produced every morning, plus a standing watch on the places you care about. This post shows how to build that with the Off-Nadir Delta MCP server — using its ready-made prompts to run a daily world briefing and an area-of-interest watch, without hand-writing the workflow each time.

It is the operational third part of a short series: giving an AI agent live world-event awareness covers the surfaces, and from a world event to the satellite scenes over it covers the imagery chain. Here we make it recurring.

What is a situation-briefing agent, and what does it do each day?

A situation-briefing agent is an AI agent that runs a fixed intelligence routine on a schedule rather than answering a single prompt. Each day it reads the current world brief, ranks where activity is concentrating, drills into the most significant event, and reports only what changed since its last run. The value is consistency: the same structured read, every day, grounded in sourced events instead of a model's training snapshot. Off-Nadir Delta exposes this as MCP prompts so the routine is one invocation, not custom glue code.

What is an MCP prompt, and why use one instead of writing your own?

An MCP prompt is a named, reusable workflow the server ships to the agent — so you invoke daily-situation-briefing instead of re-typing the instructions and tool sequence yourself. The Model Context Protocol defines three primitives an MCP server can expose: tools (actions the agent takes), resources (context it reads), and prompts (ready-made workflows). Off-Nadir Delta's server publishes four prompts over its eight tools, so an agent inherits vetted routines the moment it connects — no prompt engineering to reproduce a good briefing.

Prompt	What it runs
daily-situation-briefing	A morning briefing from the latest signals
assess-top-signal	Surface the day's highest-severity event and assess what to image next
aoi-watch	Watch an area of interest and summarize what changed and why it matters
market-exposure-check	Recent events that could move a given market, with the transmission channel (informational only)

How do you run a daily world briefing with the MCP server?

Invoke the daily-situation-briefing prompt. Behind it, the agent reads get_world_brief — the AI-synthesized Daily World Brief (headline, summary, top developments, Key Judgments), which costs no tokens — then calls query_hotspots to see where events are clustering, and assess_signal (via assess-top-signal) to drill into the day's most significant event. You get a consistent morning read: what happened, where it concentrated, and what to look at next. In an MCP client this is a single instruction, for example:

Run the daily-situation-briefing prompt, then use assess-top-signal on the highest-severity event.

Because get_world_brief and get_usage are free of token charges, the "read the brief and check my balance" part of the routine costs nothing; only the query_* and assess_signal steps spend from your token balance. The same brief also underpins the in-app Delta Watchfloor and Delta Agent, so the agent's briefing matches what a human analyst would see in the product.

How do you watch a specific area of interest for change?

Use the aoi-watch prompt, which calls query_signals scoped to a bounding box. To make it a watch rather than a re-read, the signals tool supports a differential mode: pass updated_since (or created_since) and it returns only events (re-)enriched after that timestamp — so a scheduled agent fetches the delta since its last run instead of the whole window. Results come back up to 500 signals per page, cursor-paginated, each with coordinates, a severity score, source links, and a recommended sensor. Over the REST API the same call is a plain request:

# Only security events near a bounding box that changed since the last poll
curl -H "Authorization: Bearer ond_..." \
  "https://offnadir-delta.com/api/v1/signals?bbox=30.0,50.0,31.0,51.0&categories=security&updated_since=2026-07-14T06:00:00Z&sort=severity"

An agent running aoi-watch on a schedule turns this into a standing brief: "here is what changed in your area since yesterday, ranked by severity, and here is why it matters." For the definitions behind the feed — OSINT, GEOINT, and tip-and-cue — see the glossary.

How do you keep the agent's briefing grounded and honest?

Two habits. First, keep every claim traceable: each signal in Delta Signals links back to its original sources and a verified location, so the agent can cite evidence instead of asserting it — which is what makes the feed evidence-based rather than a black box. Second, preserve uncertainty: the assess_signal and ask_analyst tools return findings with calibrated confidence written to professional analytic standards (see what a daily intelligence report is), so the agent reports "moderate confidence, single source" honestly rather than overclaiming. In practice a well-behaved briefing agent states what it knows, what it infers, and what it cannot yet confirm.

What does a daily briefing agent cost to run?

The routine's read steps are free, and the analysis steps are metered on your token balance — there is no separate seat license or per-image contract. get_world_brief and get_usage cost no tokens; query_signals, query_stats, query_hotspots, and search_imagery are billed per query; and assess_signal and ask_analyst are billed per call. Have the agent read the usage://current resource (or call get_usage) at the start of a run to pre-flight what it can spend, and it will degrade gracefully when the balance is low — brief first, deeper assessments only if budget remains. Both the API and MCP server are available on every plan, including Free; the only gate is your token balance. Current allocations live on the pricing page.

How do I connect the server to start?

Issue an API key from Account → Developer API, then register the server as an HTTP transport with your key as a bearer header. In Claude Code:

claude mcp add --transport http off-nadir-delta \
  https://offnadir-delta.com/api/v1/mcp \
  --header "Authorization: Bearer ond_..."

Any MCP client that supports HTTP transports connects the same way — Claude Code, Claude Desktop, Cursor, or VS Code — by pointing at https://offnadir-delta.com/api/v1/mcp and passing the Authorization header. Full client setup, the tool list, and the resource and prompt catalog are in the MCP server documentation.

When should you use an MCP prompt vs a REST cron job?

Use an MCP prompt when a person (or an assistant) should run the routine conversationally and read the result — a morning briefing you skim, an area watch you ask follow-up questions about. Use a REST cron job when the output feeds a machine — a dashboard tile, an alerting rule, a report generator — where you want deterministic JSON on a fixed schedule. They share the same token wallet and the same event layer, so many teams do both: a scheduled REST poll fills a common operating picture, while an MCP-connected agent answers "so what changed, and why does it matter?" For the full REST surface and config blocks, see the event intelligence API and the API & MCP reference.