
Auspice · 青鸾信 MCP server
Which servers in the official MCP registry are Auspice · 青鸾信's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-20
- Registry namecom.auspiceoracle/baziverified in the MCP registry
The registry name sits under auspiceoracle.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-20
- Tools3
- Server calls itselfauspice-bazi
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 50 ms.
- Whether its tools do the product's job has not been judged yet.
Once connected
- For "cast a bazi chart from birth time", the likely first call is cast_chart.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP score100 of 100answers 100 · definitions 100 · context 100
- Answered100% of days7 of 7 daily checks
- Median first answer120 ms
- Space in an agent's context≈ 1,563 tokensthe definitions of all its tools (3), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results3 of 3 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- can do · cast a bazi chart from birth time
- not sure · read personality patterns and life seasons
- not sure · compare two charts to examine a relationship
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
cast_chartCast a BaZi / Four Pillars chart the right way round: true solar time correction FIRST (DST + longitude + equation of time), then the four pillars with hidden stems and Na Yin, day master identity, and luck cycles. Also casts a comparison…
personality_sketchStep 1 of 2 for a personality sketch. Casts the chart and returns the chart facts plus a fill-in template (象 image / 里 beneath / 行 practice) for YOU, the assistant, to write — a short literary sketch grounded only in the returned facts…
compose_sketchStep 2 of 2 for a personality sketch: submit the three sections you wrote after personality_sketch (image / beneath / practice, in the same lang) and receive the finished framed sheet — the fixed MIRROR line, limits, quotation, link and…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"bazi": {
"type": "http",
"url": "https://auspiceoracle.com/mcp/bazi"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http auspiceoracle https://auspiceoracle.com/mcp/baziclaude.ai, ChatGPT and other clients: add https://auspiceoracle.com/mcp/bazi as a custom connector in the settings.
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.