brain-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BRAIN_VAULT_PATH | No | Absolute path to the Brain | /Users/aklingler/Documents/Projects/Obsidian/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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| brain_search_notesA | Full-text search across the Brain Obsidian vault. Searches note content for the given query string and returns matching notes with context snippets. Useful for finding notes about a topic, locating references, or discovering related content. Args: params: Search parameters including query, optional folder scope, and limit. Returns: JSON with matching notes, each containing path, title, type, match count, and context snippets. Returns an error message if no results found. |
| brain_list_notesA | List notes in a vault folder with optional filtering by type. Returns metadata for notes including path, title, type, updated date, and status. Useful for browsing a folder, reviewing inbox contents, or finding all notes of a specific type. Args: params: List parameters including folder, note_type filter, recursive flag, limit. Returns: JSON with note metadata list. Filterable by frontmatter type (moc, project, area, resource, archive). |
| brain_read_noteA | Read the full content of a specific note by path or title. Returns the complete markdown content including frontmatter, plus extracted metadata (type, wikilinks, updated date). Args: params: Either a vault-relative path or a note title. Returns: JSON with content, frontmatter metadata, and extracted wikilinks. |
| brain_create_noteA | Create a new note in the vault. By default notes are created in Notes/ per the vault workflow standard. Agent-created notes should always go to Notes/ first; promotion happens during manual vault review. Args: params: Title, content (full markdown with frontmatter), and target folder. Returns: Confirmation with the path of the created note, or an error if the note already exists. |
| brain_update_noteA | Update the content of an existing note. Replaces the full content. If update_date is True (default), the 'updated' field in frontmatter is set to today's date. Args: params: Note path or title, new content, and update_date flag. Returns: Confirmation with the updated path, or an error if not found. |
| brain_move_noteA | Move a note from one folder to another (e.g., promote from inbox). Commonly used to promote notes from Notes/ to their final location in a domain folder (Projects, Infrastructure, APIs, etc.). Args: params: Source path and destination folder. Returns: Confirmation with old and new paths, or an error. |
| brain_find_backlinksA | Find all notes that link to a given note via [[wikilinks]]. Useful for understanding how a note is referenced across the vault, checking if a note is properly linked from MOCs, or mapping relationships between concepts. Args: params: Title of the note to find backlinks for. Returns: JSON list of notes that contain [[title]] wikilinks. |
| brain_get_structureA | Get a high-level overview of the vault structure. Returns the canonical folder layout, note counts per folder, and the contents of MOC - Home for navigation. Use this as a starting point for exploring the vault. Returns: JSON with folder statistics, total note count, and MOC - Home content. |
| brain_list_foldersA | List subfolders within a vault directory. Returns immediate subdirectories and their note counts. Useful for exploring the vault hierarchy before reading specific notes. Args: folder: Optional vault-relative path. Omit for vault root. Returns: JSON list of subdirectories with note counts. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| vault_review | Review inbox for notes ready to be promoted. Lists all notes currently in Notes/ with their metadata, and provides guidance on the promotion workflow per the Vault Structure Standard. |
| kb_update | Create a KB Update note documenting a work session. Generates a pre-filled KB Update using the vault template format. The note will be created in Notes/ per the workflow standard. Args: task_name: Short name for the task (e.g., 'Delian Database Migration') context_reviewed: Notes consulted during the task (wikilinks) what_changed: Summary of what was done |
| daily_capture | Quick-capture a fleeting note to the inbox. Creates a minimal note for rapid idea capture. The note goes to Notes/ and can be expanded or promoted later. Args: topic: Optional topic or title hint for the note |
| project_status | Get a status overview of all active projects. Reads the Projects folder and summarizes active projects with their status, recent updates, and key links. |
| find_related | Find and map all notes related to a topic. Combines search, backlinks, and MOC navigation to build a comprehensive picture of how a topic is covered in the vault. Args: topic: The topic to investigate (e.g., 'Delian', 'authentication') |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/delian-research/brain-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server