astro-agents-mcpSAFE
Deterministic Western + Vedic astrology MCP server for AI agents. JPL DE440, no LLM, SHA-256 verifiable results. x402 + MPP.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Exact astrology calculations for AI agents. Use these tools instead of computing charts yourself.
- MCP endpoint:
https://astro-agent.dev/mcp(Streamable HTTP, no auth) - REST API:
https://astro-agent.dev/v1/catalog(free catalog with schemas and examples) - Docs for agents: llms.txt · OpenAPI 3.1 · A2A agent card
Why agents call it
Language models routinely get time zones, historical daylight saving, sidereal time and ayanamsa wrong, and one hour of error moves the ascendant by about 15°. Astro Agents:
- resolves the time zone and its historical offset from the coordinates (IANA tz database, DST of that era, Local Mean Time before standard time), and flags ambiguous or non-existent local times instead of guessing;
- computes positions from NASA/JPL DE440, geocentric apparent, true equinox of date (IAU 2006/2000A);
- is deterministic, with no LLM: the same input gives the same bytes. Every response carries
meta.input_sha256andmeta.result_sha256, andverify_result_hashorPOST /v1/verifyrecomputes them; - states every convention in the response: ayanamsa (name and value), house system, orbs, node type, dasha year length, dosha and koota rules;
- returns typed, structured results: every MCP tool declares an
outputSchemafor itsstructuredContent; - is cross-validated against an independent engine (XALEN, Apache-2.0): ayanamsas agree to < 0.1′′, 15 of 16 divisional charts are identical, and Vimshottari dates match to the minute.
Tools
98c1a88a4a7bOBSERVED · 2026-10-11Trust audit
SAFEgrade B · trust 88/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (3)
streamable-http
Gates applied: no_behavioural_pass, no_license.
98c1a88a4a7bfull audit observations/trust-audit/mcp-server/aidatatools-dev__astro-agents-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 98c1a88a4a7b | SAFE | B | 88 | first audit |
Questions
What is the astro-agents-mcp MCP server?
Deterministic Western + Vedic astrology MCP server for AI agents. JPL DE440, no LLM, SHA-256 verifiable results. x402 + MPP.
Is astro-agents-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (88/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does astro-agents-mcp need?
No credential environment variables were found in its source, so it appears to need none.
How does astro-agents-mcp run?
It speaks streamable-http, so it runs as a service you connect to over the network.
How current is this page?
The grade is for one exact copy of the source (98c1a88a4a7b), read on 2026-10-11. The repository is watched and re-audited when it changes.