Skip to main content
Glama

astronomy-mcp-server

by io.github.cyanheads

astronomy-mcp-server: get satellite passes

astronomy_get_satellite_passes
Read-onlyIdempotent

Predict visible passes of a satellite (e.g. the ISS, NORAD 25544) over an observer in the next days. Identify the satellite by exactly one of norad_id or name — supplying both, or neither, is rejected. name is matched as a case-insensitive substring of CelesTrak's catalog names, so it resolves only when it picks out a single object: a broader query comes back with the matching objects and their catalog numbers to choose from, and the result echoes the query that resolved it as resolved_from_name. Fetches the object's current GP element set from CelesTrak, propagates it with SGP4 in-process, and returns each pass's rise, peak, and set times with azimuths and the peak elevation. Only passes that are naked-eye-plausible are returned — the satellite must be sunlit at peak while the observer's sky is dark. Every returned pass rises within the requested window: a pass already underway at start is omitted rather than reported with start as its rise, so back up start to see it. A start further than about a month from the element set's epoch is rejected as out of range on that distance alone, and an element set that will not propagate to a window inside that horizon is rejected as a reentry — so an empty passes means only that nothing was visible. CelesTrak publishes only current element sets, so in practice start must be within about a month of today. NORAD catalog numbers and catalog names are found at celestrak.org or heavens-above.com. This is a gated, network-backed extension (CelesTrak is keyless but rate-limited; element sets are cached briefly). Default elevation 0 m; pass an IANA timezone for observer-local pass times.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
daysNoNumber of days ahead to search for passes. Default 7, max 10.
nameNoSatellite name to resolve against CelesTrak, e.g. "ISS (ZARYA)". Matched as a case-insensitive substring of the catalog name, so give the fullest name you have — a short one matches many objects and is rejected as ambiguous. Mutually exclusive with `norad_id` — supply exactly one.
startNoSearch start as an ISO 8601 UTC string, within about a month of the current element set's epoch — for a tracked object that epoch is hours old, so in practice within about a month of today. A start further out is rejected rather than answered from elements that no longer describe the orbit. Defaults to now. A value with no zone designator is read as UTC, not the local zone of the server process.
latitudeYesObserver latitude in decimal degrees, north positive.
norad_idNoNORAD catalog number of the satellite, e.g. 25544 for the ISS. Found at celestrak.org or heavens-above.com. Mutually exclusive with `name` — supply exactly one.
timezoneNoIANA timezone for localized pass times, e.g. "America/Los_Angeles". When omitted, output is UTC-only.
elevationNoObserver elevation in meters above sea level. Default 0.
longitudeYesObserver longitude in decimal degrees, east positive.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
errorNoPresent when the call failed. Absent on success.
passesNoVisible passes (sunlit satellite over a dark-enough sky) in the requested window, chronological.
norad_idNoThe NORAD catalog number echoed from the request.
totalCountNoNumber of visible passes found in the window.
satellite_nameNoSatellite name as CelesTrak catalogs it (the element set's OBJECT_NAME).
resolved_from_nameNoThe name query that resolved this object. Present only when the request supplied `name` rather than `norad_id`.

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses a wealth of behavioral details beyond the annotations: it fetches from CelesTrak, propagates with SGP4, filters for naked-eye visibility (sunlit at peak, dark sky), omits passes already underway, rejects starts too far from the element set epoch, and rejects nonexistent objects as reentries. It also mentions rate limiting and brief caching. Annotations (readOnly, idempotent, openWorld) are consistent; no contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but every sentence carries functional weight. It is logically structured: core purpose up front, then identifier constraints, then propagation and filtering behavior, then edge cases and constraints, then operational notes. While it could be trimmed slightly, the complexity of the tool warrants the detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity and the presence of an output schema (which covers return values), the description is remarkably complete. It covers all major behavioral aspects: identifier resolution, propagation method, visibility filtering, temporal constraints, error conditions (rejection criteria), and operational notes (rate limits, caching, defaults). An agent would have all necessary context to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds significant semantics: it explains the mutual exclusivity of norad_id and name, the resolution behavior and echo of `resolved_from_name`, the start window constraint relative to element set epoch, timezone handling, and default elevation. This goes well beyond the schema parameter descriptions, justifying a 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Predict visible passes of a satellite ... over an observer in the next `days`.' It clearly states the function and distinguishes it from sibling tools like ephemeris or rise/set by focusing on pass prediction with visibility filtering. The mention of the ISS and NORAD ID example grounds it concretely.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit when-to-use guidance: it mandates exactly one of `norad_id` or `name` and explains the rejection of both/neither. It details the substring matching behavior and how ambiguity is resolved, plus edge cases like passes already underway and start horizon constraints. It doesn't name sibling alternatives but the context makes it clear this is the satellite-pass tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All astronomy-mcp-server toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.6/5.0
Disambiguation5/5

Each tool targets a clearly distinct aspect of astronomy: event lookup, ephemeris for small bodies, moon phase, rise/set times, satellite passes, sky position for bodies/stars, and a visible-objects summary. Even overlapping capabilities (e.g., get_sky_position vs. get_ephemeris) are separated by scope (single instant vs. time series, major bodies vs. small bodies). No ambiguity in choosing between tools.

Naming Consistency5/5

All tool names follow a consistent pattern: 'astronomy_' prefix + descriptive verb ('find', 'get', 'list') + object. The verbs are homogeneous (mostly 'get_', plus 'find_events' and 'list_visible'), and the snake_case style is uniform. Predictable and easy to navigate.

Tool Count5/5

Seven tools is a well-scoped number for an astronomy server. Each tool covers a distinct major query type, and none feel redundant or unnecessary. This is within the ideal 3–15 range and feels neither too thin nor too heavy.

Completeness5/5

The tool set covers the full range of common astronomy asks: positions, phases, events, rise/set, satellite passes, and a 'what's up' overview. Small-body ephemerides fill the gap for non-major objects. There are no obvious dead ends; an agent can answer most user questions with these tools alone.

Resources