PluginBench
MCP Server
Active
MIT

io.github.douglasgan/asktian MCP Server

io.github.douglasgan/asktian

RepositoryRegistry
How to choose

What this kind of tool is for

  • Hand your agent a structured way to call a model or an inference API.
  • Compare outputs from two different providers on the same prompt.
  • Wire retrieval, embeddings, or generation into an existing agent workflow.

How to compare servers like this

Provider coverage:
Match the tool's supported providers and models to the ones your project uses.
Cost exposure:
Model-backed tools spend real API budget; check how usage and limits are configured.
Maintenance signal:
The provider landscape shifts weekly; prefer tools updated within the last few months.
Config surface:
Prefer tools whose environment-variable or config keys are documented plainly.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the io.github.douglasgan/asktian MCP server?

Chinese metaphysics (bazi, qimen, 5-element) as decision-support tools for AI agents.

How to install io.github.douglasgan/asktian

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • ASKTIAN_API_KEY
    secret

    OPTIONAL. Readings are free and work with no key (public backend, rate-limited to ~300 requests / 15 min). Set a key from https://api.asktian.com for higher rate limits and the premium tian.* reading tier.

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "asktian": {
      "command": "npx",
      "args": [
        "-y",
        "@asktian/mcp-server"
      ],
      "env": {
        "ASKTIAN_API_KEY": "<YOUR_ASKTIAN_API_KEY>"
      }
    }
  }
}

Related MCP servers

MIMitos logo

Mitos

Active

Architectural decision memory for LLM-native workflows — markdown for humans, a graph for agents.

4
Python
Apache-2.0
View repository →

Persistent KV memory and Q-promise deduplication for agent workflows via MCP.

14
Python
MIT
View repository →

AI claim verification MCP endpoint with x402 payments and stealth web fetch

0
Python
MIT
View repository →

Shared memory router for AI agents: save/search/recall, session-start injection, review inbox.

PEPensionPro logo

PensionPro

Maintained

MCP server for the PensionPro pension administration REST API.

0
Python
MIT
View repository →

AI task cockpit: an agent does your tasks and asks before anything irreversible.

0
MIT
View repository →