About DEVONthink
DEVONthink is an MCP server for users of DEVONthink Pro on macOS. It exposes database and record operations, including search, content management, tagging, and classification suggestions from DEVONthink AI.
Key features
- 01Search and look up records by attributes
- 02Create, delete, move, and rename records
- 03Read and modify content and properties
- 04Manage tags and database groups
- 05Get AI classification proposals and compare records
Use cases
- 01Search DEVONthink material from a client
- 02Organize records and tags in databases
- 03Review classification proposals or similar records
MCP support
The MCP server exposes DEVONthink Pro record and database operations as tools for MCP clients, including search, creation, modification, and management.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
29Saved tool list · updated 2w ago
This tool takes no parameters.
Details
From the project READMEDevonthink MCP Server
This MCP server provides access to DEVONthink functionality via the Model Context Protocol (MCP). It enables listing, searching, creating, modifying, and managing records and databases in DEVONthink Pro on macOS.

Features
- Exposes a comprehensive set of DEVONthink operations as MCP tools
- List, search, and look up records by various attributes
- Create, delete, move, and rename records and groups
- Retrieve and modify record content, properties, and tags
- Create records from URLs in multiple formats
- List open databases and group contents
- All tools are type-safe and validated with Zod schemas
Tools
Core Tools
-
is_running- Checks if DEVONthink is currently running
- No input required
- Returns:
{ "success": true | false }
-
create_record- Creates new records (notes, bookmarks, groups) with specified properties
- Input: record type, name, parent group, and optional metadata
-
delete_record- Deletes records by ID, name, or path
- Input: record identifier
-
move_record- Moves records between groups
- Input: record ID and destination group
-
get_record_properties- Retrieves detailed metadata and properties for records
- Input: record identifier
-
search- Performs text-based searches with various comparison options
- Input: query string and search options
-
lookup_record- Looks up records by filename, path, URL, tags, comment, or content hash (exact matches only)
- Input: lookup type and value
-
create_from_url- Creates records from web URLs in multiple formats
- Input: URL and format options
-
get_open_databases- Lists all currently open databases
- No input required
-
list_group_content- Lists the content of a specific group
- Input: group identifier
-
get_record_content- Retrieves the content of a specific record
- Input: record identifier
-
rename_record- Renames a specific record
- Input: record ID and new name
-
add_tags- Adds tags to a specific record
- Input: record ID and tags
-
remove_tags- Removes tags from a specific record
- Input: record ID and tags
-
classify- Gets classification proposals for a record using DEVONthink's AI
- Input: record UUID, optional database name, comparison type, and tags option
- Returns: Array of classification proposals (groups or tags) with scores
-
compare- Compares records to find similarities (hybrid approach)
- Input: primary record UUID, optional second record UUID, database name, and comparison type
- Returns: Either similar records (single mode) or detailed comparison analysis (two-record mode)
Example: Search Tool
{
"query": "project plan",
"comparison": "contains",
"database": "Inbox"
}
Returns:
{
"results": [
{ "id": "123", "name": "Project Plan", "path": "/Inbox/Project Plan.md" }
]
}
Usage with Claude
Add to your Claude configuration:
{
"mcpServers": {
"devonthink": {
"command": "npx",
"args": ["-y", "mcp-server-devonthink"]
}
}
}
Implementation Details
- Uses JXA (JavaScript for Automation) to control DEVONthink via AppleScript APIs
- All tool inputs are validated with Zod schemas for safety and clarity
- Returns structured JSON for all tool outputs
- Implements robust error handling for all operations
- Includes comprehensive tests using Vitest
See CLAUDE.md for full documentation, tool development guidelines, and API reference.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.