Holster
@kimjune01
About Holster
MCP server that will edit your claude configs
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-holster": {
"command": "python",
"args": [
"-m",
"venv",
".venv"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Holster?
Holster is a Python-based MCP server that manages other MCP servers in Claude’s desktop configuration file directly from within Claude, eliminating the need for manual text editor modifications. It is designed for users who frequently add or remove MCP servers and want to do so through Claude’s interface.
How to use Holster?
Install Holster by cloning the repository, creating a virtual environment, and installing dependencies with uv. Then add the Holster server entry to your claude_desktop_config.json (default location: ~/Library/Application Support/Claude/claude_desktop_config.json). After restarting Claude, use the provided tools (explain_holster, create_server, list_servers, update_server_status, delete_servers, ping) to manage server configurations.
Key features of Holster
- Seamless server management within Claude desktop
- JSON configuration handling with proper parsing and encoding
- Separate tracking of active and inactive servers
- Simple command-line interface
- Comprehensive test coverage
Use cases of Holster
- Adding a new MCP server configuration without editing JSON files manually
- Deactivating or reactivating existing servers on the fly
- Listing all active and inactive servers in the configuration
- Deleting server entries from the configuration file
- Checking the health of the Holster server itself
FAQ from Holster
What problem does Holster solve?
Holster replaces manual text editing of Claude’s config file when managing MCP server entries, allowing Claude to handle the task directly.
What are the runtime requirements?
Holster requires Python, a virtual environment, and uv for dependency management. It runs as a local MCP server.
Where does Holster store its data?
Holster reads and writes to ~/Library/Application Support/Claude/claude_desktop_config.json (Claude’s configuration file). It does not manage servers outside that file.
Does Holster discover or download servers automatically?
No. Server discovery and downloading are explicitly out of scope. Holster only manages configurations already present in the config file.
What transport does Holster use?
The README does not specify a transport. It is configured as a local MCP server using the uv command and holster.py script.
Frequently asked questions
What problem does Holster solve?
Holster replaces manual text editing of Claude’s config file when managing MCP server entries, allowing Claude to handle the task directly.
What are the runtime requirements?
Holster requires Python, a virtual environment, and `uv` for dependency management. It runs as a local MCP server.
Where does Holster store its data?
Holster reads and writes to `~/Library/Application Support/Claude/claude_desktop_config.json` (Claude’s configuration file). It does not manage servers outside that file.
Does Holster discover or download servers automatically?
No. Server discovery and downloading are explicitly out of scope. Holster only manages configurations already present in the config file.
What transport does Holster use?
The README does not specify a transport. It is configured as a local MCP server using the `uv` command and `holster.py` script.
Basic information
More Other MCP servers
ICSS
chokcoco不止于 CSS
Awesome Mlops
visengerA curated list of references for MLOps
Blender
ahujasidOpen-source MCP to use Blender with any LLM
YOUB
Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov
Activepieces
activepiecesAI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Comments