Skip to main content
Glama

dev_read_api

Read-onlyIdempotent

Fetch data from any allowlisted Open Ephemeris API endpoint using HTTP GET. Provides a read-only fallback for accessing endpoints not covered by typed tools.

Instructions

Read from any allowlisted Open Ephemeris API endpoint via HTTP GET. This is the read-only power-user escape hatch — use the typed tools (ephemeris_natal_chart, ephemeris_transits, etc.) first for common operations. Endpoints that compute via POST (natal-chart, synastry, etc.) are covered by the typed tools; the generic POST proxy is only exposed on the full tool surface (?profile=full).

Target API: Open Ephemeris REST API (https://api.openephemeris.com). Call dev_list_allowed to see all currently available endpoint paths.

AUTH: Set OPENEPHEMERIS_API_KEY in your environment. See openephemeris.com/dashboard for active plan limits.

CREDIT COSTS: • Standard chart math (natal, progressed, bazi, vedic, iching): 1 credit • Human Design: 2 credits • Visualization rendering (chart-wheel, bi-wheel, charts/*): 2 credits • Comparative math (synastry, composite, overlay): 3 credits • Predictive ops (transits/search, returns): 5 credits • Predictive transit-chart: 1 credit • ACG / astrocartography: 10 credits (acg/hits: 15 credits) • Calendar endpoints: 10 credits • Catalog / metadata / health endpoints: 0 credits • Compute surcharge: requests > 30s add 1 credit per 30s (predictive, acg, calendar, electional) • format=llm (token-optimized output): available on all tiers

COMMON CALLS: POST /ephemeris/natal-chart — Full natal chart (body: {subject: {name: 'Name', birth_datetime: {iso: '1990-04-15T14:30:00-05:00'}, birth_location: {latitude: {decimal: 40.0}, longitude: {decimal: -70.0}, timezone: {}}}}) POST /ephemeris/natal/batch — Up to 50 natal charts in one request POST /ephemeris/relocation — Relocated chart (same natal, new location) POST /predictive/transits/search — Transit event search over a date range POST /predictive/returns/solar — Solar return chart POST /predictive/returns/lunar — Lunar return chart POST /comparative/synastry — Two-person synastry chart POST /comparative/composite — Composite (midpoint) chart POST /human-design/chart — Full HD chart (body: {birth_datetime_utc: '1990-04-15T19:30:00Z'}) — lat/lon optional POST /time/julian-day — Convert date to JD (body: {year: 1987, month: 7, day: 15, hour: 14, minute: 1}) GET /ephemeris/moon/phase — Current/queried moon phase GET /ephemeris/moon/void-of-course — Next void-of-course period GET /ephemeris/agro/daily — Biodynamic farming day quality GET /ephemeris/agro/calendar — Multi-day biodynamic calendar GET /ephemeris/agro/void-of-course — Biodynamic VoC periods GET /eclipse/next-visible — Next eclipse visible from a location (query: lat, lon, type=solar|lunar) GET /eclipse/solar/global — Next global solar eclipse (query: date=YYYY-MM-DD) GET /eclipse/solar/local — Local solar eclipse (query: lat, lon) GET /tidal/forcing — Gravitational tidal forcing index POST /acg/power-lines — Astrocartography power lines (lat/lon GeoJSON) POST /acg/hits — ACG power at a specific location GET /calendar/astrology/moon-phases — Moon phase calendar for a date range GET /location/autocomplete — Geocode a place name (query: query=City Name) POST /timezone/lookup — Resolve timezone + UTC offset for a location POST /chinese/bazi — Chinese Ba Zi (Four Pillars) chart (body: {year, month, day, hour}) GET /chinese/zodiac — Chinese zodiac year element/animal POST /vedic/chart — Vedic (Jyotish) natal chart (body: {datetime_utc, latitude, longitude}) GET /catalogs/bodies — List all supported celestial bodies

BINARY RESPONSES: • Binary/image endpoints return {content_type, content_length, encoding, data_base64} so callers can decode bytes deterministically.

ECLIPSE NOTE: Eclipse endpoints accept format=llm via the query param like other endpoints.

format=llm NOTE: Add query: {format: 'llm'} to natal/synastry/composite/HD endpoints for compact columnar output optimized for LLM token budgets (availability depends on your current plan).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bodyNoJSON request body (optional)
pathYesAbsolute API path (e.g., /ephemeris/natal-chart)
queryNoQuery params (optional)
formatNoConvenience: if provided, set query.format (optional). 'llm' is canonical; 'llm_v2' is accepted as a legacy alias.
methodNoHTTP method (always GET)
presetNoConvenience: if provided, set query.preset (optional).
output_modeNoLegacy convenience (deprecated): if provided, set query.output_mode and also map to query.preset/query.format when possible.
Install Server

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already establish readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavior beyond annotations: credit costs, binary response envelope shape, format=llm behavior, and auth requirements. It loses a point because it lists POST endpoints under 'COMMON CALLS' even though the tool only supports GET, creating avoidable ambiguity about what is actually callable through this proxy.

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 well-structured with clear sections (auth, credit costs, common calls, binary responses, format notes), and important guidance is front-loaded. However, it is quite long and has some redundancy (format=llm is mentioned multiple times), and the extensive endpoint example list could be trimmed without losing essential meaning.

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

Completeness4/5

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 absence of an output schema, the description covers most operational needs: auth, credit implications, endpoint discovery, common request bodies, binary response handling, and format options. It is not fully complete because it doesn't explicitly state that the listed POST endpoints are not callable through this GET-only proxy, and it omits error/rate-limit response behavior.

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

Parameters3/5

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

Schema description coverage is 100%, so the baseline is 3; the schema already documents path, body, query, format, method, preset, and output_mode. The description adds some useful context, such as format=llm being token-optimized and preset/output_mode conveniences, but it does not materially deepen per-parameter semantics beyond what the input schema provides.

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 clearly identifies the tool as a read-only generic HTTP GET proxy to allowlisted Open Ephemeris endpoints, using a specific verb ('Read'), resource ('API endpoint'), and mechanism ('HTTP GET'). It also distinguishes itself from the typed sibling tools by labeling itself the 'power-user escape hatch' and says the typed tools should be preferred for common operations.

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 explicitly tells the agent when to use this tool versus alternatives: use typed tools first for common operations, and only use this generic proxy for allowlisted endpoints not covered by typed tools. It also names the sibling dev_list_allowed for discovering allowed paths, which is exactly the kind of routing guidance an agent needs.

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

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/openephemeris/openephemeris-MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server