Knowledge MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | debug / info / warn / error | info |
| GITHUB_REPO | Yes | Tên repo chứa brain | |
| CACHE_TTL_MS | No | Thời gian cache file reads (ms) | 30000 |
| GITHUB_OWNER | Yes | Username hoặc org trên GitHub | |
| GITHUB_TOKEN | Yes | GitHub Personal Access Token (quyền repo) | |
| GITHUB_BRANCH | No | Branch sử dụng | main |
| WRITE_RETRIES | No | Số lần retry khi gặp SHA conflict | 3 |
| BRAIN_BASE_PATH | No | Thư mục gốc trong repo | brain |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| initBrainA | Initialize the brain repository structure. Creates all required folders and markdown files in a single commit. Only needs to be called once on a new/empty repo. |
| getTasksC | Get all tasks grouped by file (today + backlog). Returns tasks with id, text, status, tags, priority, dueDate. |
| getTodayTasksB | Get all tasks from today's task list |
| getBacklogB | Get all tasks from the backlog |
| addTaskB | Add a new task to today's list or the backlog |
| markTaskDoneB | Mark a task as complete. Provide either a taskId (from getTasks) or searchText to fuzzy-match the task. |
| getNotesC | Get notes from the ideas or learning section |
| addNoteC | Add a note to the ideas or learning section |
| getGoalsC | Get goals from short-term or long-term sections |
| getInboxB | Get all items from the inbox/capture list |
| saveToInboxC | Save a quick thought, idea, or item to the inbox for later processing |
| listTopicsA | List all knowledge topics. Returns topic names only (no content). Use this first to discover what knowledge exists before reading. |
| getKnowledgeA | Get all entries from a specific knowledge topic. Use listTopics first to see available topics. |
| addKnowledgeA | Add a new knowledge entry to a topic. Creates the topic if it doesn't exist. Use this to store facts, how-tos, decisions, or anything worth remembering. |
| searchKnowledgeC | Search across all knowledge topics by keyword. Returns matching entries with their topic, title, and content. |
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 15 tools
Most tools have distinct purposes, but there is some overlap between 'addNote' and 'addKnowledge' (both store information) and between 'getTasks', 'getTodayTasks', and 'getBacklog' (all retrieve tasks with different scopes). Descriptions help clarify boundaries, but an agent might occasionally misselect between these related tools.
Tool names follow a highly consistent verb_noun pattern throughout, such as 'addKnowledge', 'getTasks', 'listTopics', and 'saveToInbox'. All tools use camelCase uniformly, with no mixing of naming conventions, making them predictable and easy to understand.
With 15 tools, the server is well-scoped for a knowledge management system, covering tasks, notes, knowledge entries, and inbox items. Each tool serves a clear purpose, and the count is appropriate for handling the domain's core workflows without being overwhelming.
The tool set provides comprehensive coverage for knowledge and task management, including CRUD operations for tasks (add, get, mark done) and knowledge (add, get, list, search), with inbox and notes support. Minor gaps include no update or delete tools for knowledge entries or notes, but agents can work around this by adding new entries or using other methods.