TheBrain MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VERBOSE | No | Set to true to enable verbose logging and debug mode. | |
| THEBRAIN_API_KEY | Yes | Your TheBrain API key required for authentication. | |
| THEBRAIN_DEFAULT_BRAIN_ID | No | Optional default brain ID to use for operations. |
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 |
|---|---|
| list_brainsA | List all available brains for the user |
| get_brainC | Get details about a specific brain |
| set_active_brainC | Set the active brain for subsequent operations |
| create_thoughtC | Create a new thought with optional visual properties |
| update_thoughtB | Update a thought including its visual properties |
| create_linkB | Create a link between two thoughts with visual properties |
| update_linkC | Update link properties including visual formatting |
| add_file_attachmentB | Add a file attachment (including images) to a thought |
| add_url_attachmentB | Add a URL attachment to a thought |
| get_attachment_contentC | Get the binary content of an attachment (e.g., download an image) |
| get_noteB | Get the note content for a thought |
| create_or_update_noteC | Create or update a note with markdown content |
| append_to_noteC | Append content to an existing note |
| search_thoughtsC | Search for thoughts in a brain |
| get_thoughtC | Get details about a specific thought |
| get_thought_graphC | Get a thought with all its connections and attachments |
| delete_thoughtC | Delete a thought |
| get_linkB | Get details about a specific link |
| delete_linkC | Delete a link |
| get_attachmentC | Get metadata about an attachment |
| delete_attachmentC | Delete an attachment |
| list_attachmentsC | List all attachments for a thought |
| get_typesC | Get all thought types in a brain |
| get_tagsC | Get all tags in a brain |
| get_brain_statsC | Get statistics about a brain |
| get_modificationsB | Get modification history for a brain |
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 26 tools
Each tool has a clear, distinct purpose. For example, get_thought retrieves basic thought data while get_thought_graph includes connections and attachments. Even similar actions like append_to_note and create_or_update_note are well-differentiated by their descriptions.
All tools follow a consistent verb_noun pattern with underscores (e.g., create_thought, get_attachment, delete_link). The verbs are uniform and descriptive, making the pattern predictable and easy to follow.
At 26 tools, the set is on the high side but still justified given the complexity of TheBrain's features (thoughts, notes, links, attachments, brains, tags, etc.). Each tool serves a specific operation, and there is minimal redundancy.
The tool surface covers the full lifecycle of thoughts, notes, links, attachments, and brain management. Operations include create, read, update, delete, search, and listing. No obvious gaps are apparent for the stated domain.