Docs Navigator MCP - SUSE Edition
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AI_PROVIDER | No | AI provider (ollama, openai, anthropic) | ollama |
| OLLAMA_MODEL | No | Ollama model for Q&A | llama3.2:latest |
| OPENAI_API_KEY | No | OpenAI API key (required if using OpenAI provider) | |
| USE_JSON_CACHE | No | Use JSON cache instead of SQLite | false |
| VECTOR_DB_PATH | No | Path to vector database directory | ./data/vectors |
| EMBEDDING_MODEL | No | Embedding model name | nomic-embed-text |
| OLLAMA_BASE_URL | No | Ollama server URL | http://localhost:11434 |
| PAGE_CACHE_PATH | No | Path to SQLite page cache | ./data/page-cache.db |
| FETCH_BATCH_SIZE | No | Number of pages to fetch concurrently | 5 |
| ANTHROPIC_API_KEY | No | Anthropic API key (required if using Anthropic provider) | |
| EMBEDDING_PROVIDER | No | Embedding provider (ollama, openai) | ollama |
| EMBEDDING_CACHE_PATH | No | Path to embedding cache JSON | ./data/embedding-cache.json |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_docsA | Search SUSE, Rancher, K3s, and related documentation using semantic search. Returns relevant documentation sections. |
| get_doc_sectionB | Retrieve a specific section of documentation by URL or identifier. |
| summarize_docA | Generate an AI-powered summary of a documentation page or section using open-source models. |
| ask_questionA | Ask a question about SUSE documentation. The AI will search relevant docs and provide an answer with sources. |
| index_documentationA | Index documentation from specified sources for faster searching. This should be run initially or to update the index. |
| list_doc_sourcesA | List all available documentation sources and their status. |
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 6 tools
Each tool has a clear, distinct purpose: direct retrieval, semantic search, summarization, Q&A, index management, and source listing. No two tools overlap in function, and the descriptions clearly differentiate them.
All tool names follow the verb_noun pattern with lowercase and underscores. The verbs (get, search, summarize, ask, index, list) are consistent and the nouns are descriptive. Minor singular/plural variations do not detract from the overall pattern.
The server has 6 tools, which is well within the ideal range. Each tool serves a necessary function for a documentation navigator, with no redundant or superfluous tools.
The tool surface covers the core workflows of a documentation navigator: indexing sources, searching, retrieving specific sections, summarizing, and asking questions. There are no obvious dead ends or missing operations for the stated purpose.