Knowledge Assistant MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KNOWLEDGE_CACHE_TTL | No | Durée du cache en secondes | 60 |
| KNOWLEDGE_INDEX_PATH | No | Chemin du fichier d'index (Défaut: ~/.knowledge/notes-index.json ou %USERPROFILE%\.knowledge\notes-index.json) | |
| KNOWLEDGE_VAULT_PATH | No | Chemin du vault Obsidian (Défaut: ~/Documents/Knowledge ou %USERPROFILE%\Documents\Knowledge) |
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
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| knowledge_searchB | Search notes in the Knowledge vault by content or title. Returns matching notes with snippets. |
| knowledge_readB | Read the full content of a specific note. Use the path from search results or the note title. |
| knowledge_relatedB | Find notes related to a concept (by links, tags, or mentions). |
| knowledge_statsB | Get statistics about the Knowledge vault (total notes, types, tags, recent notes). |
| knowledge_explore_tagB | Find all notes with a specific tag. |
| knowledge_backlinksC | Find all notes that link to a specific note (backlinks). |
| knowledge_recentC | Get recently modified notes. |
| knowledge_writeA | Create a new note in the Knowledge vault with proper frontmatter and naming conventions. Naming conventions: C_ for concepts, YYYY-MM-DD_Conv_ for conversations, YYYY-MM-DD_Fix_ for troubleshooting notes. Checks for duplicates before creation. |
| knowledge_graphA | Generate a graph view of links between notes. Without center_note, returns the most connected clusters. With center_note, returns the subgraph around that note. Output is JSON with nodes[] and edges[] compatible with graph visualizations. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Vault Statistics | Statistics about the Knowledge vault |
TDQS
Scored across 9 tools
Each tool has a clearly distinct purpose with no overlap: backlinks, tag exploration, graph generation, reading, recent notes, related concepts, search, statistics, and writing. The descriptions specify unique operations, making tool selection unambiguous for an agent.
All tools follow a consistent 'knowledge_' prefix with descriptive suffixes (e.g., backlinks, explore_tag, graph), using snake_case uniformly. This predictable pattern enhances readability and reduces cognitive load for agents.
With 9 tools, the set is well-scoped for a knowledge management server, covering core operations like CRUD (create, read, search), exploration (graph, related, tags), and analytics (stats, recent). Each tool earns its place without bloat.
The tool surface provides complete coverage for knowledge management: create (write), read, search, and explore (graph, related, tags, backlinks), plus analytics (stats, recent). There are no obvious gaps, enabling agents to handle full note lifecycles and discovery workflows.