chinese-history-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| STORYEXTRACTOR_DB | Yes | Path to the corpus database file |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_eventsA | 查跨书融合历史事件 + 逐源出处。同一史事在史记/汉书/资治通鉴等多书的记载被合并为一条, 每个来源带【书·篇·段】与角色 (主叙/详述/简述/评论/旁证)。返回 review_status (approved=机审批量过审的可信推定, 非逐条人审); canonical_summary 为 LLM 融合的机器叙述。 |
| get_personA | 查人物画像 + 他者评价 + 参与事件 (逐条带出处)。画像 (profile) 为 LLM 综合生成、review_status=draft (未逐条人核); 他者评价 excerpt 是公版原文照抄可溯源; 附史料评为的品质。库内为先秦-汉魏人物。 |
| query_by_placeA | 用今天的地名反查发生在这块土地上的古籍故事 + 出处。今地名可为省/地级市/区县 (如 '西安'、'陕西西安'、'洛阳')。古今映射多为多 LLM 机审共识 (auto_approved); 同名异地/古名多解时返回候选列表让你消歧, 绝不替你单选; 方向性泛称 (江东/关中) 不收录。 |
| query_by_qualityA | 按品质 (德性/才能/性情/为政…) 查代表性最强的事件/人物/故事 + 原文证据。品质取自 55 词受控词表 (如 忠/谋略/勇/仁/残暴/骄), 可用中文名或英文 slug。映射是【判断】非事实: auto_approved=机审高置信、draft=待人审; evidence_quote 是原文真子串; 默认只出机审通过。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool targets a distinct search dimension: events, persons, places, and qualities. The descriptions clearly separate their use cases, leaving no ambiguity about which tool to select for a given query.
Most tools follow a clear verb_noun pattern (search_events, get_person), while two use query_by_ (place, quality). This minor deviation is still readable and doesn't confuse the overall naming convention.
With 4 tools, the server is well-scoped for its purpose. Each tool earns its place, covering different aspects of Chinese history knowledge without redundancy or bloat.
The toolset covers core search dimensions (event, person, place, quality), but lacks time-based or dynasty-specific queries and direct source text retrieval. These are minor gaps that agents can work around using the provided tools.