LLM Wiki MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CHAT_MODEL | No | Chat model name | deepseek-chat |
| EMBED_MODEL | No | Embedding model name | text-embedding-3-small |
| EMBED_API_KEY | No | Embedding API key (required when EMBED_PROVIDER=api) | |
| EMBED_API_URL | No | Embedding API URL | |
| EMBED_PROVIDER | No | Embedding mode: api / local / off | local |
| OPENAI_API_KEY | No | LLM chat API key (needed for ingest and --llm mode) | |
| OPENAI_BASE_URL | No | Compatible OpenAI API endpoint, e.g., https://api.deepseek.com |
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": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ingestA | 编译一份原始素材为 Wiki 页（提取概念/建链/标矛盾）。 |
| queryA | 混合检索 + 链接扩展，返回相关 Wiki 片段。 |
| write_wikiA | 新建一个 Wiki 页（自动生成 frontmatter）。 |
| read_wikiA | 读取一个 Wiki 页全文（含 frontmatter）。 |
| rebuild_indexA | 全量重建向量 + BM25 索引（从现有 Wiki 页）。 |
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 5 tools
Each tool targets a distinct operation: query for retrieval, write_wiki for creating pages, read_wiki for reading pages, rebuild_index for indexing maintenance, and ingest for processing raw material into wiki pages. There is minimal overlap, and descriptions clarify any potential confusion.
The naming pattern is mixed: two tools use verb_noun style (write_wiki, read_wiki), one uses verb_noun but for a different object (rebuild_index), while two tools are single-word verbs (query, ingest). This inconsistency makes the set less predictable, though still readable.
With 5 tools, the set is well-scoped for a wiki server, covering creation, reading, searching, indexing, and ingestion. It is neither too thin nor too heavy, and each tool serves a clear purpose.
The set covers create, read, query, index rebuild, and ingestion, but notably lacks update and delete operations for wiki pages. This creates a gap in the typical CRUD lifecycle, which agents may need to work around.