Discover how to integrate Bear note-taking with MCP server for seamless note management and automation
The Bear MCP Server is a specialized adapter designed to facilitate seamless integration between various AI applications, such as Claude Desktop, Continue, Cursor, and others, with the Bear note-taking software. This server acts as an intermediary, allowing these AI tools to interact with Bear's functionalities through a standardized Model Context Protocol (MCP). By leveraging this protocol, developers can ensure that their AI solutions are easily extendable and compatible with a wide range of data sources and applications.
The Bear MCP Server offers a comprehensive set of features aligned with the Model Context Protocol. These include actions such as opening notes, creating new ones, adding text or files, managing tags, searching through content, and more. Each action corresponds to specific X-callback-url commands detailed in Bear’s official documentation.
graph TD
classDef standard fill:#8C62B5;
classDef compatible fill:#CA849D;
classDef core(fill:#E28A71, stroke:#fff, stroke-width:2px);
classDef protocol(compatStroke:#03A89F, mainColor:#FFEB3B, compatFont:#c46aa7);
A[Open Note] --> B{熊}
B --> C(Checked)
D[Create New Note] --> E{创建新笔记}
E --> F(Checked)
G[Add Text/Files] --> H{添加文本/文件}
H --> I(Checked)
J[Tags Management] --> K{标签管理}
K --> L(Checked)
M[Search & Filtering] --> N{搜索与过滤}
N --> O(Checked)
P[Trash & Archive] --> Q{回收站与归档}
Q --> R(Checked)
S[TBD]
class A core
class B protocol
class C standard
class D core
class E protocol
class F standard
class G core
class H protocol
class I standard
class J core
class K protocol
class L standard
class M core
class N protocol
class O standard
class P core
class Q protocol
class R standard
class S compatible
These actions enable AI applications to perform common tasks within Bear, enhancing their functionality and usability.
The architecture of the Bear MCP Server is built around the Model Context Protocol (MCP), ensuring compatibility with a variety of other MCP-compliant clients. The server acts as an endpoint for these clients to perform operations on Bear's note data. By adhering to the MCP, the server ensures that interactions are consistent and predictable across different AI tools.
The implementation involves several key components:
BEAR_API_TOKEN
is required for authentication.extensions:
bear:
name: Bear
cmd: uvx
args: [--from, git+https://github.com/jkawamoto/mcp-bear, mcp-bear]
envs: { "BEAR_API_TOKEN": "<YOUR_TOKEN>" }
enabled: true
type: stdio
To enable the Bear extension in Goose CLI, follow these steps:
~/.config/goose/config.yaml
and add the following entry.<YOUR_TOKEN>
with your actual API token for auth.Adding a new extension is straightforward:
uvx --from git+https://github.com/jkawamoto/mcp-bear mcp-bear
BEAR_API_TOKEN
with your API tokenTo configure this server in Claude Desktop, edit the claude_desktop_config.json
file and include the following entry:
{
"mcpServers": {
"bear": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/jkawamoto/mcp-bear",
"mcp-bear",
"--token",
"<YOUR_TOKEN>"
]
}
}
}
After editing, restart the application.
To install Bear MCP Server for Claude Desktop using Smithery:
npx -y @smithery/cli install @jkawamoto/mcp-bear --client claude
The Bear MCP Server can be used in various AI workflows, enabling seamless integration between AI models and note-taking applications. Below are two examples:
Imagine a scenario where an AI application automatically synthesizes notes based on research or project outcomes. Using the Bear MCP Server, the AI tool can invoke actions such as open-note
and add-text
, allowing it to insert synthesized text directly into Bear's note-taking framework. This ensures that all generated content is organized effectively.
Another use case involves automating the collection of data from diverse sources and saving them in Bear notes. For instance, an AI model could be configured to monitor specific news feeds or project updates, then automatically generate and store relevant notes using Bear MCP Server's capabilities such as search
and add-file
.
The Bear MCP Server is compatible with several MCP clients:
graph TD
A[AI Application] -->|MCP Client| B[MCP Protocol]
B --> C[MCP Server]
C --> D[Data Source/Tool]
style A fill:#e1f5fe;
style C fill:#f3e5f5;
style D fill:#e8f5e8;
MCP Client | Resources | Tools | Prompts | Status |
---|---|---|---|---|
Claude Desktop | ✅ | ✅ | ✅ | Full Support |
Continue | ✅ | ✅ | ❌ | Tools Only |
Cursor | ❌ | ✅ | ❌ | Tools Only |
Advanced users can customize the server by configuring environment variables and command-line arguments. The BEAR_API_TOKEN
ensures secure API authentication, while additional settings allow fine-tuning of behavior to meet specific needs.
graph LR
subgraph MCP_Servers
A[Server Endpoint]
B[MCP Client Requests]
end
subgraph Bear_Application
C[API Token Auth]
D[X-callback-url Scheme Invocation]
E[Data Storage & Management]
end
F[Data Sources]
A -->|HTTP/TLS| B
B --> C
C -->|Auth| D
D --> E
E -->|DB| F
style MCP_Servers fill:#f3e5f5;
style Bear_Application fill:#e8f5e8;
style F fill:#caefca;
A: It ensures compatibility and seamless integration, enabling advanced features in AI workflows.
A: Yes, though full support is only available for some clients. Refer to the compatibility matrix for details.
A: Use environment variables to store sensitive information securely and avoid hardcoding in configuration files.
A: Currently, it is specifically designed for Bear but can inspire similar implementations for other tools.
A: Detailed documentation is available on the official Model Context Protocol website and GitHub repositories.
Contributors are welcome to enhance this MCP server. Please follow these guidelines:
For more resources and information on Model Context Protocol, visit:
This comprehensive documentation positions the Bear MCP Server as a powerful tool for integrating AI applications with note-taking software. By leveraging its capabilities and understanding of the Model Context Protocol, developers can create advanced workflows that enhance productivity and efficiency.
RuinedFooocus is a local AI image generator and chatbot image server for seamless creative control
Learn to set up MCP Airflow Database server for efficient database interactions and querying airflow data
Simplify MySQL queries with Java-based MysqlMcpServer for easy standard input-output communication
Build stunning one-page websites track engagement create QR codes monetize content easily with Acalytica
Access NASA APIs for space data, images, asteroids, weather, and exoplanets via MCP integration
Explore CoRT MCP server for advanced self-arguing AI with multi-LLM inference and enhanced evaluation methods