# Wenbu · 问卜 (remote · wenbu.app)

Free BaZi, I Ching, tarot, Zi Wei and bilingual learning tools with transparent methods. No API key.

- Trust score: 82/100 (high trust)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `wenbu.app`: 82/100 (this document), [markdown](https://verifymcp.io/servers/app-wenbu-mcp/wenbu.md), [page](https://verifymcp.io/servers/app-wenbu-mcp/wenbu)

## Channel facts

- Endpoint: `https://wenbu.app/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.3.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 68/100
  - 80% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 626 tokens (~62/item across 10 items; 7 tools + 3 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 73/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 4% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Wenbu · 问卜 MCP server?

Wenbu · 问卜 is a hosted endpoint at https://wenbu.app/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http app-wenbu-mcp 'https://wenbu.app/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "app-wenbu-mcp": {
      "url": "https://wenbu.app/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "app-wenbu-mcp": {
      "type": "http",
      "url": "https://wenbu.app/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.app-wenbu-mcp]
url = "https://wenbu.app/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "app-wenbu-mcp": {
      "type": "remote",
      "url": "https://wenbu.app/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add app-wenbu-mcp --url 'https://wenbu.app/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  app-wenbu-mcp:
    url: "https://wenbu.app/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "app-wenbu-mcp": {
      "Transport": "http",
      "Url": "https://wenbu.app/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add app-wenbu-mcp -t streamable-http -u 'https://wenbu.app/mcp'
```

### Other

```json
{
  "mcpServers": {
    "app-wenbu-mcp": {
      "type": "http",
      "url": "https://wenbu.app/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-02 (score 82, +1)

- [security] Stability: 0.97 → pass

### 2026-10-31 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 79, +1)

- [security] Tool “read_library” rewrote its description, which is the text the model reads

### 2026-10-25 (score 78, +3)

- [functional regression] Schema quality: 497 → 603
- [functional improvement] Schema quality: 50% → 80%
- [functional improvement] Tool “calculate_bazi” now declares an output schema
- [functional improvement] Tool “calculate_ziwei” now declares an output schema
- [functional improvement] Tool “cast_iching” now declares an output schema
- [functional improvement] Tool “draw_tarot” now declares an output schema
- [functional improvement] Tool “read_library” now declares an output schema
- [functional improvement] Tool “search_library” now declares an output schema
- [functional] The server now declares the “prompts” capability
- [functional] First check of Tool coverage: 100
- [functional] New prompt “reflect_on_reading”
- [functional] New prompt “research_with_sources”
- [functional] New resource “capabilities”
- [functional] Server version: 1.4.0 → 1.5.0
- [functional] New tool “get_daily_card”
- [cosmetic] “calculate_bazi” reworded the description of “timezone”
- [cosmetic] Tool “calculate_bazi” changed its title: calculate bazi
- [cosmetic] Tool “calculate_ziwei” changed its title: calculate ziwei
- [cosmetic] Tool “cast_iching” changed its title: cast iching
- [cosmetic] Tool “draw_tarot” changed its title: draw tarot
- [cosmetic] Tool “read_library” changed its title: read library
- [cosmetic] Tool “search_library” changed its title: search library

### 2026-10-23 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-19 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (7)

### `calculate_bazi` (~102 tokens)

calculate bazi

Calculate four pillars. Unknown time returns no hour pillar. Gregorian date, IANA timezone, explicit day boundary. No prediction.

Input parameters:

- `date` (string, required)
- `dayBoundary` (string)
- `locale` (string)
- `longitude` (number)
- `solarTime` (boolean)
- `time`
- `timezone` (string): Birthplace IANA zone or explicit offset. If omitted, Asia/Shanghai is assumed and disclosed.

Output parameters:

- `calendar` (object)
- `dayMaster` (object)
- `elements` (array)
- `input` (object)
- `kind` (string)
- `method` (object)
- `pillars` (array)
- `version` (string)
- `warnings` (array)

### `cast_iching` (~61 tokens)

cast iching

Cast six three-coin lines or supply your own. Lines are ordered bottom to top, values 6/7/8/9. Returns original and changed King Wen hexagrams.

Input parameters:

- `lines` (array)
- `locale` (string)

Output parameters:

- `changed` (object)
- `kind` (string)
- `lines` (array)
- `method` (object)
- `moving` (array)
- `original` (object)
- `version` (string)

### `draw_tarot` (~54 tokens)

draw tarot

Draw one or three cards from a full 78-card deck without replacement. Reversals optional. Symbolic reflection only.

Input parameters:

- `count`
- `locale` (string)
- `reversals` (boolean)

Output parameters:

- `cards` (array)
- `kind` (string)
- `method` (object)
- `version` (string)

### `calculate_ziwei` (~73 tokens)

calculate ziwei

Calculate Zi Wei Dou Shu twelve palaces from an entered local civil date and known time. iztro default school, no solar-time correction. Sex is a traditional calculation parameter.

Input parameters:

- `date` (string, required)
- `locale` (string)
- `sex` (string, required)
- `time` (string, required)

Output parameters:

- `body` (string)
- `fiveElementsClass` (string)
- `input` (object)
- `kind` (string)
- `lunarDate` (string)
- `method` (object)
- `palaces` (array)
- `soul` (string)
- `time` (string)
- `version` (string)

### `search_library` (~62 tokens)

search library

Search Wenbu original guides, symbols and curated reference metadata. This is a bounded catalogue, not a web search. Search snippets do not mean the source was read.

Input parameters:

- `limit` (integer)
- `locale` (string)
- `query` (string, required)

Output parameters:

- `results` (array)

### `read_library` (~112 tokens)

read library

Read a complete Wenbu guide or symbol by search_library ID. Handbook guides return Markdown, outline and export links without truncation. Optionally provide a section ID from the outline; the returned scope makes partial reads explicit. A corrected stale citation returns source_superseded with a current-document read action, not withdrawn content or read evidence. External reference entries are metadata only; use your host browsing capability to verify them.

Input parameters:

- `id` (string, required)
- `locale` (string)
- `section` (string)

Output parameters:

- `content` (string)
- `documentId` (string)
- `format` (string)
- `links` (object)
- `outline` (array)
- `scope` (string)
- `section` (string|null)
- `source` (object)
- `truncated` (boolean)

### `get_daily_card` (~69 tokens)

get daily card

Get a public daily reflection card and practice using the server calendar in an IANA timezone. No model, account, personal history or quota turn. Can differ from a personal browser/account card. Keep the returned result for follow-up.

Input parameters:

- `locale` (string)
- `timezone` (string)

Output parameters:

- `clock` (object)
- `note` (string)
- `practice` (object)
- `result` (object)
- `scope` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/app-wenbu-mcp/wenbu#diagnostics

## Score history

- 2026-11-05: 82
- 2026-11-04: 82
- 2026-11-03: 82
- 2026-11-02: 82
- 2026-11-01: 81
- 2026-10-31: 81
- 2026-10-30: 80
- 2026-10-29: 80
- 2026-10-28: 79
- 2026-10-27: 79
- 2026-10-26: 78
- 2026-10-25: 78
- 2026-10-24: 75
- 2026-10-23: 75
- 2026-10-22: 74
- 2026-10-21: 74
- 2026-10-20: 73
- 2026-10-19: 73
- 2026-10-18: 72
- 2026-10-17: 72
- 2026-10-16: 71
- 2026-10-15: 71
- 2026-10-14: 71
- 2026-10-13: 70
- 2026-10-12: 70
- 2026-10-10: 69
- 2026-10-07: 67
- 2026-10-04: 66
- 2026-10-03: 65

## Common questions

### What is the Wenbu · 问卜 MCP server?

Wenbu · 问卜 is an MCP server listed in the public MCP registry as app.wenbu/mcp. Free BaZi, I Ching, tarot, Zi Wei and bilingual learning tools with transparent methods. No API key. This page covers its hosted endpoint (https://wenbu.app/mcp).

### Is the Wenbu · 问卜 MCP server safe to use?

Wenbu · 问卜 scores 82 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Wenbu · 问卜 MCP server expose?

Wenbu · 问卜 exposes 7 tools: calculate_bazi, cast_iching, draw_tarot, calculate_ziwei, search_library, and 2 more. Their descriptions and schemas cost roughly 533 tokens of context every time the server is loaded.

### Does the Wenbu · 问卜 MCP server require authentication?

No. We connected to Wenbu · 问卜 without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Wenbu · 问卜 MCP server still maintained?

Wenbu · 问卜 is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Wenbu · 问卜 MCP server?

VerifyMCP ran 13 checks on Wenbu · 问卜, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://wenbu.app/mcp
- Repository: https://github.com/wenbu-app/wenbu
- Website: https://wenbu.app/en/agents/?utm_source=mcp-registry&utm_medium=referral&utm_campaign=mcp-registry
- Changelog RSS feed: https://verifymcp.io/servers/app-wenbu-mcp/wenbu.xml
- Changelog JSON feed: https://verifymcp.io/servers/app-wenbu-mcp/wenbu/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/app-wenbu-mcp/wenbu.json
- HTML version of this page: https://verifymcp.io/servers/app-wenbu-mcp/wenbu