global-sentinel-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Python log level (DEBUG/INFO/WARNING/ERROR) | INFO |
| OPENSKY_PASSWORD | No | OpenSky Basic Auth password (legacy) | |
| OPENSKY_USERNAME | No | OpenSky Basic Auth username (legacy) | |
| OPENSKY_CLIENT_ID | No | OpenSky OAuth2 client id (preferred) | |
| CLOUDFLARE_API_TOKEN | No | Cloudflare API token with Radar read permissions | |
| OPENSKY_CLIENT_SECRET | No | OpenSky OAuth2 client secret (preferred) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_prediction_oddsA | Search Polymarket for crowd-sourced probability estimates. Use this tool when the user asks "what are the odds of X?" for any
macro-relevant event — Fed rate decisions, elections, geopolitical
outcomes, commodities. Returns up to Example: |
| get_prediction_event_by_idA | Fetch a single Polymarket event's implied probability by id or slug. Useful when you already have a Polymarket event identifier (from a prior search, a URL, or an external reference) and want the current odds without re-searching. |
| lookup_aircraft_stateA | Return the latest public ADS-B state vector for a registered aircraft. Accepts either an FAA N-Number (e.g. Returns position (lat/lon), barometric altitude (m), ground speed (m/s),
heading (°), on-ground flag, and last-contact timestamp. Requires
|
| convert_nnumberA | Convert between an FAA N-Number and its ICAO24 hex address. Input detection is automatic: a leading |
| get_global_eventsA | Fetch recent high-impact GDELT 2.0 events for a country. GDELT publishes a new global event export every 15 minutes. Events are
coded with a Goldstein scale from -10 (destabilizing) to +10 (stabilizing).
Pass a 3-letter GDELT country code (e.g. Results are sorted by Goldstein scale descending and capped at |
| check_network_anomaliesA | Check Cloudflare Radar for BGP and internet-outage anomalies. Input formats:
Requires |
| get_macro_alertA | Composite macro-inflection signal for a region. Runs three queries concurrently (GDELT events, BGP hijacks, outages) and
emits a single Score weighting: |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool targets a distinct domain: network anomalies, aviation identifiers, geopolitical events, composite alerts, and prediction markets. No two tools perform overlapping functions, so agents can easily distinguish them.
All tool names use snake_case with descriptive verbs like 'check_', 'convert_', 'get_', and 'lookup_'. While different verbs are used, they are appropriate to each action and follow a predictable pattern, with only minor variation.
With 7 tools, the set is well-scoped for a global monitoring server. Each tool provides a specific, non-redundant capability, and the count is manageable for an agent to navigate without being overwhelming or sparse.
The tool surface covers network anomalies, aviation, geopolitical events, and prediction markets, but lacks some expected features like news search or natural disaster monitoring. For a 'sentinel' purpose, there are notable gaps, though core workflows are supported.